# agent-memory-server - Doramagic AI Context Pack

> Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated.

## Sufficiency Principle

- **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary.
- **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work.

## How the Host AI Should Use This

You are reading the AI Context Pack that Doramagic compiled for agent-memory-server. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project.

## Claim Consumption Rules

- **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure.
- **Minimum status for a fact**: `supported`
- `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path.
- `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying.
- `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact.
- `unverified`: Must not be used as fact; state clearly that evidence is insufficient.
- `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf.

## Who It Fits Best

- **Users who want to understand an open-source project's value and boundaries before installing**: Current evidence comes mainly from project documentation. Evidence: `README.md` Claim: `clm_0002` supported 0.86

## What It Can Do

- **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al. Claim: `clm_0001` supported 0.86

## How to Start

- `pip install agent-memory-client httpx openai` Evidence: `V0/docs/agent-examples.md` Claim: `clm_0003` supported 0.86
- `curl -H "Authorization: Bearer YOUR_TOKEN" \` Evidence: `V0/docs/authentication.md` Claim: `clm_0004` supported 0.86
- `curl -H "Authorization: Bearer YOUR_API_TOKEN" \` Evidence: `V0/docs/authentication.md` Claim: `clm_0005` supported 0.86
- `curl -H "Authorization: Bearer YOUR_JWT_TOKEN" \` Evidence: `V0/docs/authentication.md` Claim: `clm_0006` supported 0.86
- `curl -H "Content-Type: application/json" \` Evidence: `V0/docs/authentication.md` Claim: `clm_0007` supported 0.86
- `pip install agent-memory-server[aws]` Evidence: `V0/docs/aws-bedrock.md` Claim: `clm_0008` supported 0.86
- `pip install uv` Evidence: `V0/docs/getting-started.md` Claim: `clm_0009` supported 0.86, `clm_0025` supported 0.86
- `pip install agent-memory-client langchain-core` Evidence: `V0/docs/langchain-integration.md` Claim: `clm_0010` supported 0.86
- `pip install agent-memory-client langchain langchain-openai langgraph` Evidence: `V0/docs/langchain-integration.md` Claim: `clm_0011` supported 0.86
- `curl -X PUT "http://localhost:8000/v1/working-memory/my-session" \` Evidence: `V0/docs/memory-extraction-strategies.md` Claim: `clm_0012` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Trial role matching first
- **Why**: This project is more of a role library; the core risk is picking the wrong role or treating role copy as execution capability. Trial role matching with Prompt Preview first, then decide whether to sandbox-import it.

### 30-Second Read

- **What to do now**: Trial role matching first
- **Minimum safe next step**: Trial role matching with Prompt Preview first; import in isolation only once satisfied
- **Do not trust yet**: Role quality and task fit cannot be trusted directly.
- **Continuing will touch**: Role selection bias, Command execution, Host AI configuration

### What You Can Trust Now

- **Target-audience signal: Users who want to understand an open-source project's value and boundaries before installing** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `README.md` Claim: `clm_0002` supported 0.86
- **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al. Claim: `clm_0001` supported 0.86
- **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `V0/docs/agent-examples.md` Claim: `clm_0003` supported 0.86

### What You Cannot Trust Yet

- **Role quality and task fit cannot be trusted directly.** (unverified): A role library proves there are many roles; it does not prove each one fits your specific task or that a role produces high-quality results.
- **Do not treat role copy as real execution capability.** (unverified): Before install you can only judge whether the role description and task profile match; you cannot prove it can complete the task inside the host AI.
- **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project.
- **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment.
- **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `AGENTS.md`, `CLAUDE.md`, `V0/AGENTS.md`
- **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first.
- **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment.
- **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.

### What Continuing Will Touch

- **Role selection bias**: The user's judgment about which expert role should handle the task. Why: Picking the wrong role makes the AI answer from the wrong expert perspective, wasting time or misleading decisions.
- **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al.
- **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `AGENTS.md`, `CLAUDE.md`, `V0/AGENTS.md`
- **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al.
- **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts.

### Minimum Safe Next Steps

- **Run Prompt Preview first**: Use an interactive trial to verify the task profile and role match first; do not import the whole role library up front. (applies when: Applies to any project, especially when output quality is unknown.)
- **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.)
- **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.)
- **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.)

### Exit Plan

- **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable.
- **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state.
- **Keep a record of the original role selection**: If output goes off-topic, you can return to the task-profiling stage and reselect a role instead of pushing on with the wrong one.
- **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually.
- **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck.

## What Can Only Be Previewed

- Explain who the project fits and what it can do
- Demonstrate a typical conversation flow based on project docs
- Help the user decide whether it is worth installing or researching further

## What Must Be Verified After Install

- Actually installing the Skill, plugin, or CLI
- Running scripts, modifying local files, or accessing external services
- Verifying real output quality, performance, and compatibility

## Boundary & Risk Decision Card

- **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0027` inferred 0.45
- **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al. Claim: `clm_0028` supported 0.86
- **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment.
- **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation.
- **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments.

## Pre-Work Working Context

### Loading Order

- First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset.
- Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative.
- Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match.
- When you need to carry out a concrete task, check role_skill_index first, then evidence_index.
- For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required.

### Task Routes

- **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `V0/AGENTS.md`, `V0/agent-memory-client/README.md`, `V0/docs/agent-examples.md`, `V0/docs/authentication.md` et al. Claim: `clm_0001` supported 0.86

### Context Scale

- Total files: 232
- Important-file coverage: 40/232
- Evidence index entries: 80
- Role / Skill entries: 50

### Handling Insufficient Evidence

- **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts.
- **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install.
- **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run.
- **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version.

## Prompt Recipes

### Fit assessment

- Goal: Judge whether this project fits the user's current task.
- Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation.

```text
Based on the AI Context Pack for agent-memory-server, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id.
```

### Pre-install experience

- Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise.
- Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language.

```text
Treat agent-memory-server as a pre-install experience asset, not an already-installed tool or a real runtime environment.

Output exactly four parts:
1. Ask me 3 necessary questions first.
2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow.
3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run.
4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project.

Hard boundaries:
- Do not claim you have installed, run, executed tests, modified files, or produced real results.
- Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing".
- If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...".
- The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating".
- Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment.
- Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions.

```

### Role / Skill selection

- Goal: Pick the best-matching asset from the project's roles or Skills.
- Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed.

```text
Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs.
```

### Risk pre-check

- Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting.
- Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items.

```text
Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have.
```

### Host AI kickoff instruction

- Goal: Turn the project context into a host AI instruction for the start of a conversation.
- Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI.

```text
Based on the AI Context Pack for agent-memory-server, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results.
```

## Role / Skill Index

- Indexed 50 role / Skill / project-doc entries.

- **Redis Agent Memory Server Documentation** (project_doc): Redis Agent Memory Server Documentation Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/README.md`
- **Redis Agent Memory** (project_doc): A memory layer that gives agents intelligent short-term memory and persistent context across conversations. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md`
- **Redis Agent Memory Server** (project_doc): Documentation https://redis.github.io/agent-memory-server/ • GitHub https://github.com/redis/agent-memory-server • Docker https://hub.docker.com/r/redislabs/agent-memory-server Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/README.md`
- **Agent Memory Client** (project_doc): A Python client library for the Agent Memory Server https://github.com/redis-developer/agent-memory-server REST API, providing comprehensive memory management capabilities for AI agents and applications. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/agent-memory-client/README.md`
- **Agent Memory Client JavaScript/TypeScript** (project_doc): Agent Memory Client JavaScript/TypeScript Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/agent-memory-client/agent-memory-client-js/README.md`
- **Examples** (project_doc): This directory contains example implementations showing how to use the Agent Memory Server with the agent memory client SDK. Examples use LangChain's modern create agent API LangGraph-based for agent orchestration. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/examples/README.md`
- **Manual OAuth QA Testing Guide** (project_doc): This folder contains everything needed to manually test Auth0 authentication with the Redis Memory Server on any machine. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/manual_oauth_qa/README.md`
- **Agent Memory Workbench** (project_doc): A browser-based demo UI for the Redis Agent Memory Server ../README.md . It provides two interactive views — a Memory Explorer for browsing and managing long-term memories, and a Chat interface that demonstrates memory-augmented conversations using OpenAI. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/workbench/README.md`
- **AGENTS.md** (project_doc): The project source, build tooling, tests, and docs live in V0/ ./V0/ . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `AGENTS.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (project_doc): CLAUDE.md - Redis Agent Memory Server Project Context Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CLAUDE.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (project_doc): CLAUDE.md - Redis Agent Memory Server Project Context Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/AGENTS.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (project_doc): CLAUDE.md - Redis Agent Memory Server Project Context Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/CLAUDE.md`
- **Advanced Memory Vector Database Configuration** (project_doc): Advanced Memory Vector Database Configuration Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/advanced-memory-vector-db.md`
- **Advanced Topics** (project_doc): Optimize memory search, tune ranking algorithms, and configure advanced memory vector database features. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/advanced-topics-index.md`
- **Agent Examples** (project_doc): This section provides comprehensive working examples that demonstrate real-world usage patterns of the Redis Agent Memory Server. Each example showcases different aspects of memory management, from basic conversation storage to advanced memory editing workflows. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/agent-examples.md`
- **API Reference** (project_doc): Complete reference documentation for all Redis Agent Memory Server interfaces and client SDKs. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/api-reference-index.md`
- **REST API Reference** (project_doc): This documentation is auto-generated from the OpenAPI specification. For interactive docs, run the server and visit /docs . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/api.md`
- **Authentication** (project_doc): The Redis Agent Memory Server supports multiple authentication modes for secure API access. All API endpoints except /v1/health , /docs , and /openapi.json require valid authentication unless disabled for development. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/authentication.md`
- **AWS Bedrock Models** (project_doc): The Redis Agent Memory Server supports Amazon Bedrock https://aws.amazon.com/bedrock/ for both embedding models and LLM generation models . This allows you to use AWS-native AI models while keeping your data within the AWS ecosystem. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/aws-bedrock.md`
- **Command Line Interface** (project_doc): The agent-memory-server provides a command-line interface CLI for managing the server and related tasks. You can access the CLI using the agent-memory command assuming the package is installed in a way that makes the script available in your PATH, e.g., via pip install ... . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/cli.md`
- **Configuration** (project_doc): The Redis Agent Memory Server can be configured via environment variables or YAML configuration files. All settings have sensible defaults for development, but you'll want to customize them for production. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/configuration.md`
- **Contextual Grounding** (project_doc): Contextual grounding is an advanced feature that ensures extracted memories contain complete, unambiguous information by resolving pronouns, temporal references, and other contextual elements within the full conversation history. This eliminates confusion from vague references like "he," "yesterday," or "that place" in stored memories. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/contextual-grounding.md`
- **Custom Memory Vector Databases** (project_doc): The Agent Memory Server uses a flexible factory system that allows you to plug in custom memory vector database implementations. By default, the server uses Redis for vector indexing and search over long term memories, but you can override this by providing your own factory function. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/custom-memory-vector-db.md`
- **Developer Guide** (project_doc): Learn how to integrate memory into your AI applications. This guide covers integration patterns, memory types, extraction strategies, and memory lifecycle management. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/developer-guide-index.md`
- **Development** (project_doc): Start by creating a virtual environment and installing dependencies with uv: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/development.md`
- **Embedding Providers** (project_doc): The Redis Agent Memory Server uses LiteLLM for embeddings, enabling support for many embedding providers out of the box. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/embedding-providers.md`
- **Getting Started** (project_doc): Get up and running with Redis Agent Memory Server. Whether you want a quick 5-minute setup or a comprehensive installation guide, start here. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/getting-started-index.md`
- **Getting Started** (project_doc): First, you'll need to download this repository. After you've downloaded it, you can install and run the servers. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/getting-started.md`
- **Redis Agent Memory Server** (project_doc): Give your AI agents persistent memory and context that gets smarter over time. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/index.md`
- **Java SDK** (project_doc): The Java SDK agent-memory-client-java provides a type-safe client for integrating memory capabilities into JVM-based applications. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/java-sdk.md`
- **LangChain Integration** (project_doc): The Python SDK agent-memory-client provides a LangChain integration that helps you use the memory server with LangChain applications. This integration automatically converts memory operations into LangChain-compatible tools. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/langchain-integration.md`
- **LLM Providers** (project_doc): The Redis Agent Memory Server uses LiteLLM https://docs.litellm.ai/ as a unified interface for all LLM operations. This enables support for 100+ LLM providers without code changes—just configure environment variables. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/llm-providers.md`
- **Long-term Memory** (project_doc): Long-term memory is persistent , cross-session storage designed for knowledge that should be retained and searchable across all interactions. It's the "knowledge base" of facts, preferences, and experiences the agent learns at runtime. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/long-term-memory.md`
- **MCP Server Interface** (project_doc): Agent Memory Server offers an MCP Model Context Protocol server interface powered by FastMCP, providing tool-based memory management for LLMs and agents: Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/mcp.md`
- **Memory Extraction Strategies** (project_doc): This reference documents the configurable extraction strategies that determine how memories are extracted from conversations during background extraction memory-integration-patterns.md pattern-3-background-extraction-automatic . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/memory-extraction-strategies.md`
- **Memory Integration Patterns** (project_doc): The most common question developers have is: "How do I actually get memories into and out of my LLM?" Redis Agent Memory Server provides three distinct patterns for integrating memory with your AI applications, each optimized for different use cases and levels of control. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/memory-integration-patterns.md`
- **Memory Lifecycle Management** (project_doc): Redis Agent Memory Server provides sophisticated memory lifecycle management to prevent unlimited growth and maintain optimal performance. This includes automatic background forgetting processes, memory compaction strategies, and server-controlled cleanup operations. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/memory-lifecycle.md`
- **Operations Guide** (project_doc): Configure, secure, and deploy your Redis Agent Memory Server in production. This guide covers server configuration, authentication, LLM providers, and infrastructure setup. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/operations-guide-index.md`
- **Python SDK** (project_doc): The Python SDK provides a simple, async-first interface for integrating memory into your AI applications. It includes client libraries, tool schemas for LLMs, and framework integrations. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/python-sdk-index.md`
- **Python SDK** (project_doc): The Python SDK agent-memory-client provides the easiest way to integrate memory into your AI applications. It includes high-level abstractions, tool integration for OpenAI and Anthropic, and automatic function call resolution. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/python-sdk.md`
- **Query Optimization** (project_doc): The Redis Agent Memory Server includes intelligent query optimization that uses configurable language models to improve search accuracy and retrieval quality. This feature automatically refines user queries to better match stored memories using specialized AI models. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/query-optimization.md`
- **Quick Start Guide** (project_doc): Get up and running with Redis Agent Memory Server in 5 minutes. This guide shows you how to build memory-enabled AI applications using the Python SDK, with REST API examples as backup. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/quick-start.md`
- **Recency Boost** (project_doc): Recency boost is an intelligent memory ranking system that combines semantic similarity with time-based relevance to surface the most contextually appropriate memories. It ensures that recent and frequently accessed memories are weighted appropriately in search results while maintaining semantic accuracy. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/recency-boost.md`
- **Security Guide: Custom Memory Prompts** (project_doc): Security Guide: Custom Memory Prompts Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/security-custom-prompts.md`
- **Summary Views** (project_doc): Summary Views provide configurable, partitioned summaries of long-term memories. They enable applications to generate and cache concise overviews of memory collections, organized by user, namespace, session, or other groupings. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/summary-views.md`
- **TypeScript SDK** (project_doc): The TypeScript SDK agent-memory-client provides a type-safe client for integrating memory capabilities into Node.js and browser applications. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/typescript-sdk.md`
- **Use Cases and Examples** (project_doc): Redis Agent Memory Server enables powerful AI applications by providing persistent, searchable memory. Here are real-world use cases and implementation examples across different industries and applications. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/use-cases.md`
- **Working Memory** (project_doc): Working memory stores the current conversation for a session. It holds messages, tracks context, and automatically summarizes old messages when the conversation gets too long. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/docs/working-memory.md`
- **Release Process for Agent Memory Client Java** (project_doc): Release Process for Agent Memory Client Java Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/agent-memory-client/agent-memory-client-java/RELEASE.md`
- **Auth0 Troubleshooting Guide** (project_doc): This guide helps you diagnose and fix common Auth0 authentication issues. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `V0/manual_oauth_qa/TROUBLESHOOTING.md`

## Evidence Index

- Indexed 80 evidence entries.

- **Redis Agent Memory Server Documentation** (documentation): Redis Agent Memory Server Documentation Evidence: `V0/docs/README.md`
- **Redis Agent Memory** (documentation): A memory layer that gives agents intelligent short-term memory and persistent context across conversations. Evidence: `README.md`
- **Redis Agent Memory Server** (documentation): Documentation https://redis.github.io/agent-memory-server/ • GitHub https://github.com/redis/agent-memory-server • Docker https://hub.docker.com/r/redislabs/agent-memory-server Evidence: `V0/README.md`
- **Agent Memory Client** (documentation): A Python client library for the Agent Memory Server https://github.com/redis-developer/agent-memory-server REST API, providing comprehensive memory management capabilities for AI agents and applications. Evidence: `V0/agent-memory-client/README.md`
- **Agent Memory Client JavaScript/TypeScript** (documentation): Agent Memory Client JavaScript/TypeScript Evidence: `V0/agent-memory-client/agent-memory-client-js/README.md`
- **Examples** (documentation): This directory contains example implementations showing how to use the Agent Memory Server with the agent memory client SDK. Examples use LangChain's modern create agent API LangGraph-based for agent orchestration. Evidence: `V0/examples/README.md`
- **Manual OAuth QA Testing Guide** (documentation): This folder contains everything needed to manually test Auth0 authentication with the Redis Memory Server on any machine. Evidence: `V0/manual_oauth_qa/README.md`
- **Agent Memory Workbench** (documentation): A browser-based demo UI for the Redis Agent Memory Server ../README.md . It provides two interactive views — a Memory Explorer for browsing and managing long-term memories, and a Chat interface that demonstrates memory-augmented conversations using OpenAI. Evidence: `V0/workbench/README.md`
- **AGENTS.md** (documentation): The project source, build tooling, tests, and docs live in V0/ ./V0/ . Evidence: `AGENTS.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (documentation): CLAUDE.md - Redis Agent Memory Server Project Context Evidence: `CLAUDE.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (documentation): CLAUDE.md - Redis Agent Memory Server Project Context Evidence: `V0/AGENTS.md`
- **CLAUDE.md - Redis Agent Memory Server Project Context** (documentation): CLAUDE.md - Redis Agent Memory Server Project Context Evidence: `V0/CLAUDE.md`
- **Package** (package_manifest): { "name": "agent-memory-client", "version": "0.3.2", "description": "JavaScript/TypeScript client for the Agent Memory Server REST API", "main": "dist/index.js", "module": "dist/index.mjs", "types": "dist/index.d.ts", "exports": { ".": { "types": "./dist/index.d.ts", "import": "./dist/index.mjs", "require": "./dist/index.js" } }, "files": "dist", "README.md", "LICENSE" , "scripts": { "build": "tsup", "dev": "tsup --watch", "test": "vitest", "test:coverage": "vitest --coverage", "lint": "eslint src --ext .ts", "lint:fix": "eslint src --ext .ts --fix", "format": "prettier --write src/ / .ts", "typecheck": "tsc --noEmit", "prepublishOnly": "npm run build" }, "keywords": "redis", "memory", "age… Evidence: `V0/agent-memory-client/agent-memory-client-js/package.json`
- **Package** (package_manifest): { "name": "agent-memory-workbench", "private": true, "version": "0.1.0", "type": "module", "scripts": { "dev": "vite", "build": "tsc -b && vite build", "lint": "eslint .", "preview": "vite preview", "format": "prettier --write \"src/ / .{ts,tsx,css}\"" }, "dependencies": { "@tanstack/react-query": "^5.56.2", "clsx": "^2.1.1", "lucide-react": "^0.462.0", "openai": "^4.73.0", "react": "^18.3.1", "react-dom": "^18.3.1", "react-router-dom": "^7.18.1", "sonner": "^1.5.0", "tailwind-merge": "^2.5.2" }, "devDependencies": { "@eslint/js": "^9.9.0", "@tailwindcss/postcss": "^4.0.0", "@types/node": "^22.5.0", "@types/react": "^18.3.5", "@types/react-dom": "^18.3.0", "@vitejs/plugin-react-swc": "^4.3.… Evidence: `V0/workbench/package.json`
- **License** (source_file): Copyright c 2025 Redis, Inc. Released under the Apache License 2.0: Evidence: `LICENSE`
- **License** (source_file): Copyright c 2025 Redis, Inc. Released under the Apache License 2.0: Evidence: `V0/agent-memory-client/LICENSE`
- **Advanced Memory Vector Database Configuration** (documentation): Advanced Memory Vector Database Configuration Evidence: `V0/docs/advanced-memory-vector-db.md`
- **Advanced Topics** (documentation): Optimize memory search, tune ranking algorithms, and configure advanced memory vector database features. Evidence: `V0/docs/advanced-topics-index.md`
- **Agent Examples** (documentation): This section provides comprehensive working examples that demonstrate real-world usage patterns of the Redis Agent Memory Server. Each example showcases different aspects of memory management, from basic conversation storage to advanced memory editing workflows. Evidence: `V0/docs/agent-examples.md`
- **API Reference** (documentation): Complete reference documentation for all Redis Agent Memory Server interfaces and client SDKs. Evidence: `V0/docs/api-reference-index.md`
- **REST API Reference** (documentation): This documentation is auto-generated from the OpenAPI specification. For interactive docs, run the server and visit /docs . Evidence: `V0/docs/api.md`
- **Authentication** (documentation): The Redis Agent Memory Server supports multiple authentication modes for secure API access. All API endpoints except /v1/health , /docs , and /openapi.json require valid authentication unless disabled for development. Evidence: `V0/docs/authentication.md`
- **AWS Bedrock Models** (documentation): The Redis Agent Memory Server supports Amazon Bedrock https://aws.amazon.com/bedrock/ for both embedding models and LLM generation models . This allows you to use AWS-native AI models while keeping your data within the AWS ecosystem. Evidence: `V0/docs/aws-bedrock.md`
- **Command Line Interface** (documentation): The agent-memory-server provides a command-line interface CLI for managing the server and related tasks. You can access the CLI using the agent-memory command assuming the package is installed in a way that makes the script available in your PATH, e.g., via pip install ... . Evidence: `V0/docs/cli.md`
- **Configuration** (documentation): The Redis Agent Memory Server can be configured via environment variables or YAML configuration files. All settings have sensible defaults for development, but you'll want to customize them for production. Evidence: `V0/docs/configuration.md`
- **Contextual Grounding** (documentation): Contextual grounding is an advanced feature that ensures extracted memories contain complete, unambiguous information by resolving pronouns, temporal references, and other contextual elements within the full conversation history. This eliminates confusion from vague references like "he," "yesterday," or "that place" in stored memories. Evidence: `V0/docs/contextual-grounding.md`
- **Custom Memory Vector Databases** (documentation): The Agent Memory Server uses a flexible factory system that allows you to plug in custom memory vector database implementations. By default, the server uses Redis for vector indexing and search over long term memories, but you can override this by providing your own factory function. Evidence: `V0/docs/custom-memory-vector-db.md`
- **Developer Guide** (documentation): Learn how to integrate memory into your AI applications. This guide covers integration patterns, memory types, extraction strategies, and memory lifecycle management. Evidence: `V0/docs/developer-guide-index.md`
- **Development** (documentation): Start by creating a virtual environment and installing dependencies with uv: Evidence: `V0/docs/development.md`
- **Embedding Providers** (documentation): The Redis Agent Memory Server uses LiteLLM for embeddings, enabling support for many embedding providers out of the box. Evidence: `V0/docs/embedding-providers.md`
- **Getting Started** (documentation): Get up and running with Redis Agent Memory Server. Whether you want a quick 5-minute setup or a comprehensive installation guide, start here. Evidence: `V0/docs/getting-started-index.md`
- **Getting Started** (documentation): First, you'll need to download this repository. After you've downloaded it, you can install and run the servers. Evidence: `V0/docs/getting-started.md`
- **Redis Agent Memory Server** (documentation): Give your AI agents persistent memory and context that gets smarter over time. Evidence: `V0/docs/index.md`
- **Java SDK** (documentation): The Java SDK agent-memory-client-java provides a type-safe client for integrating memory capabilities into JVM-based applications. Evidence: `V0/docs/java-sdk.md`
- **LangChain Integration** (documentation): The Python SDK agent-memory-client provides a LangChain integration that helps you use the memory server with LangChain applications. This integration automatically converts memory operations into LangChain-compatible tools. Evidence: `V0/docs/langchain-integration.md`
- **LLM Providers** (documentation): The Redis Agent Memory Server uses LiteLLM https://docs.litellm.ai/ as a unified interface for all LLM operations. This enables support for 100+ LLM providers without code changes—just configure environment variables. Evidence: `V0/docs/llm-providers.md`
- **Long-term Memory** (documentation): Long-term memory is persistent , cross-session storage designed for knowledge that should be retained and searchable across all interactions. It's the "knowledge base" of facts, preferences, and experiences the agent learns at runtime. Evidence: `V0/docs/long-term-memory.md`
- **MCP Server Interface** (documentation): Agent Memory Server offers an MCP Model Context Protocol server interface powered by FastMCP, providing tool-based memory management for LLMs and agents: Evidence: `V0/docs/mcp.md`
- **Memory Extraction Strategies** (documentation): This reference documents the configurable extraction strategies that determine how memories are extracted from conversations during background extraction memory-integration-patterns.md pattern-3-background-extraction-automatic . Evidence: `V0/docs/memory-extraction-strategies.md`
- **Memory Integration Patterns** (documentation): The most common question developers have is: "How do I actually get memories into and out of my LLM?" Redis Agent Memory Server provides three distinct patterns for integrating memory with your AI applications, each optimized for different use cases and levels of control. Evidence: `V0/docs/memory-integration-patterns.md`
- **Memory Lifecycle Management** (documentation): Redis Agent Memory Server provides sophisticated memory lifecycle management to prevent unlimited growth and maintain optimal performance. This includes automatic background forgetting processes, memory compaction strategies, and server-controlled cleanup operations. Evidence: `V0/docs/memory-lifecycle.md`
- **Operations Guide** (documentation): Configure, secure, and deploy your Redis Agent Memory Server in production. This guide covers server configuration, authentication, LLM providers, and infrastructure setup. Evidence: `V0/docs/operations-guide-index.md`
- **Python SDK** (documentation): The Python SDK provides a simple, async-first interface for integrating memory into your AI applications. It includes client libraries, tool schemas for LLMs, and framework integrations. Evidence: `V0/docs/python-sdk-index.md`
- **Python SDK** (documentation): The Python SDK agent-memory-client provides the easiest way to integrate memory into your AI applications. It includes high-level abstractions, tool integration for OpenAI and Anthropic, and automatic function call resolution. Evidence: `V0/docs/python-sdk.md`
- **Query Optimization** (documentation): The Redis Agent Memory Server includes intelligent query optimization that uses configurable language models to improve search accuracy and retrieval quality. This feature automatically refines user queries to better match stored memories using specialized AI models. Evidence: `V0/docs/query-optimization.md`
- **Quick Start Guide** (documentation): Get up and running with Redis Agent Memory Server in 5 minutes. This guide shows you how to build memory-enabled AI applications using the Python SDK, with REST API examples as backup. Evidence: `V0/docs/quick-start.md`
- **Recency Boost** (documentation): Recency boost is an intelligent memory ranking system that combines semantic similarity with time-based relevance to surface the most contextually appropriate memories. It ensures that recent and frequently accessed memories are weighted appropriately in search results while maintaining semantic accuracy. Evidence: `V0/docs/recency-boost.md`
- **Security Guide: Custom Memory Prompts** (documentation): Security Guide: Custom Memory Prompts Evidence: `V0/docs/security-custom-prompts.md`
- **Summary Views** (documentation): Summary Views provide configurable, partitioned summaries of long-term memories. They enable applications to generate and cache concise overviews of memory collections, organized by user, namespace, session, or other groupings. Evidence: `V0/docs/summary-views.md`
- **TypeScript SDK** (documentation): The TypeScript SDK agent-memory-client provides a type-safe client for integrating memory capabilities into Node.js and browser applications. Evidence: `V0/docs/typescript-sdk.md`
- **Use Cases and Examples** (documentation): Redis Agent Memory Server enables powerful AI applications by providing persistent, searchable memory. Here are real-world use cases and implementation examples across different industries and applications. Evidence: `V0/docs/use-cases.md`
- **Working Memory** (documentation): Working memory stores the current conversation for a session. It holds messages, tracks context, and automatically summarizes old messages when the conversation gets too long. Evidence: `V0/docs/working-memory.md`
- **This should never be reached, but mypy needs to know this never returns** (source_file): TOOL SEARCH MEMORY = "search memory" TOOL GET OR CREATE WORKING MEMORY = "get or create working memory" TOOL LAZILY CREATE LONG TERM MEMORY = "lazily create long term memory" TOOL UPDATE WORKING MEMORY DATA = "update working memory data" TOOL GET LONG TERM MEMORY = "get long term memory" TOOL EAGERLY CREATE LONG TERM MEMORY = "eagerly create long term memory" TOOL EDIT LONG TERM MEMORY = "edit long term memory" TOOL DELETE LONG TERM MEMORIES = "delete long term memories" TOOL GET CURRENT DATETIME = "get current datetime" ⋮---- TOOL ADD MEMORY TO WORKING MEMORY = "add memory to working memory" TOOL CREATE LONG TERM MEMORY = "create long term memory" ⋮---- class OpenAIFunctionCall TypedDict ⋮… Evidence: `V0/agent-memory-client/agent_memory_client/client.py`
- **Filters** (source_file): class BaseFilter BaseModel ⋮---- class SessionId BaseFilter ⋮---- eq: str None = None in : list str None = None not eq: str None = None not in: list str None = None startswith: str None = None ⋮---- class Namespace BaseFilter ⋮---- class UserId BaseFilter ⋮---- class Topics BaseFilter ⋮---- any: list str None = None all: list str None = None none: list str None = None ⋮---- class Entities BaseFilter ⋮---- class CreatedAt BaseFilter ⋮---- gte: datetime None = None lte: datetime None = None eq: datetime None = None ⋮---- class LastAccessed BaseFilter ⋮---- class EventDate BaseFilter ⋮---- class MemoryType BaseFilter ⋮---- class ExtractionStrategy BaseFilter Evidence: `V0/agent-memory-client/agent_memory_client/filters.py`
- **Models** (source_file): logger = logging.getLogger name ⋮---- JSONTypes = str float int bool list Any dict str, Any None ⋮---- ModelNameLiteral = Literal ⋮---- class MemoryTypeEnum str, Enum ⋮---- EPISODIC = "episodic" SEMANTIC = "semantic" MESSAGE = "message" ⋮---- class SearchModeEnum str, Enum ⋮---- KEYWORD = "keyword" HYBRID = "hybrid" ⋮---- class SearchScoreTypeEnum str, Enum ⋮---- class MemoryStrategyConfig BaseModel ⋮---- strategy: Literal "discrete", "summary", "preferences", "custom" = Field config: dict str, Any = Field ⋮---- class MemoryMessage BaseModel ⋮---- warned message ids: ClassVar set str = set warned message ids lock: ClassVar threading.Lock = threading.Lock max warned ids: ClassVar int = 10000… Evidence: `V0/agent-memory-client/agent_memory_client/models.py`
- **Return None only when no model information is provided** (source_file): logger = get logger name tiktoken encoding: Any None = None tiktoken encoding last failed at: float None = None TIKTOKEN ENCODING RETRY INTERVAL SECONDS = 300 ⋮---- router = APIRouter ⋮---- model config = LLMClient.get model config model name ⋮---- def calculate messages token count messages: list MemoryMessage - int ⋮---- def get tiktoken encoding - Any None ⋮---- now = time.monotonic last failed at = tiktoken encoding last failed at retry after = ⋮---- tiktoken encoding = tiktoken.get encoding "cl100k base" tiktoken encoding last failed at = None ⋮---- tiktoken encoding last failed at = now ⋮---- def estimate text token count text: str - int ⋮---- def count text tokens text: str - int ⋮--… Evidence: `V0/agent_memory_server/api.py`
- **Auth** (source_file): logger = structlog.get logger ⋮---- class UserInfo BaseModel ⋮---- sub: str aud: str list str None = None scope: str None = None exp: int None = None iat: int None = None iss: str None = None email: str None = None roles: list str None = None ⋮---- class TokenInfo BaseModel ⋮---- description: str created at: datetime expires at: datetime None = None token hash: str ⋮---- class JWKSCache ⋮---- def init self, cache duration: int = 3600 ⋮---- def get jwks self, jwks url: str - dict str, Any ⋮---- current time = time.time ⋮---- response = client.get jwks url ⋮---- jwks data = response.json ⋮---- jwks cache = JWKSCache oauth2 scheme = HTTPBearer auto error=False ⋮---- def get jwks url - str ⋮---… Evidence: `V0/agent_memory_server/auth.py`
- **Get the memory vector database** (source_file): logger = get logger name ⋮---- VERSION = version DEFAULT REDELIVERY TIMEOUT MULTIPLIER = 2 ⋮---- def default redelivery timeout seconds - int ⋮---- @click.group def cli ⋮---- @cli.command def version ⋮---- @cli.command def rebuild index ⋮---- """Rebuild the search index.""" ⋮---- async def setup and run ⋮---- Get the memory vector database db = await get memory vector db ⋮---- Only Redis implementation supports index rebuilding ⋮---- index = db.index ⋮---- @cli.command def migrate memories ⋮---- async def run migrations ⋮---- redis = await get redis conn migrations = ⋮---- def migrate working memory batch size: int, dry run: bool ⋮---- async def run migration ⋮---- string keys = cursor = 0… Evidence: `V0/agent_memory_server/cli.py`
- **The session token is optional only for STS .** (source_file): logger = logging.getLogger name ⋮---- class ModelProvider str, Enum ⋮---- OPENAI = "openai" ANTHROPIC = "anthropic" AWS BEDROCK = "aws-bedrock" OTHER = "other" ⋮---- class ModelConfig BaseModel ⋮---- provider: ModelProvider name: str max tokens: int embedding dimensions: int = 1536 ⋮---- MODEL CONFIGS = { ⋮---- class Settings BaseSettings ⋮---- redis url: str = "redis://localhost:6379" long term memory: bool = True openai api key: str None = None anthropic api key: str None = None openai api base: str None = None anthropic api base: str None = None generation model: str = "gpt-5" embedding model: str = "text-embedding-3-small" ⋮---- region name: str None = None ⋮---- aws access key id: str… Evidence: `V0/agent_memory_server/config.py`
- **Backwards compatibility alias** (source_file): logger = get logger name ⋮---- class HybridBackgroundTasks BackgroundTasks ⋮---- def add task self, func: Callable ..., Any , args: Any, kwargs: Any - None ⋮---- def run in thread ⋮---- async def schedule task ⋮---- future = executor.submit run in thread ⋮---- Backwards compatibility alias DocketBackgroundTasks = HybridBackgroundTasks ⋮---- def get background tasks - HybridBackgroundTasks ⋮---- """ Dependency function that returns a HybridBackgroundTasks instance. NOTE: This function is deprecated. Use HybridBackgroundTasks directly as a type annotation in your endpoint instead of Depends get background tasks . Example: Old way deprecated : async def endpoint background tasks=Depends get ba… Evidence: `V0/agent_memory_server/dependencies.py`
- The remaining 20 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`.

## Rules the Host AI Must Follow

- **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `V0/docs/README.md`, `README.md`, `V0/README.md`
- **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `V0/docs/README.md`, `README.md`, `V0/README.md`

## Questions the User Should Answer First

- Which host AI or local environment do you plan to use it in?
- Do you just want to experience the workflow first, or are you ready to actually install?
- What matters most to you: install cost, output quality, or conflicts with your existing rules?

## Acceptance Checks

- Every capability claim can be traced back to a file path in evidence_refs.
- AI_CONTEXT_PACK.md does not package previews as a real run.
- The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes.

---

## Doramagic Context Augmentation

The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.

## Human Manual Outline

Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.

Host AI hard rules:
- Do not treat page titles, section order, summaries, or importance values as factual project evidence.
- When explaining the Human Manual outline, state that it is only a reading route or salience signal.
- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.

- **Overview and System Architecture**: importance `high`
  - source_paths: README.md, V0/README.md, V0/agent_memory_server/main.py, V0/agent_memory_server/api.py, V0/agent_memory_server/docket_tasks.py
- **Core Memory Features: Working Memory, Long-Term Memory, Search, and Extraction**: importance `high`
  - source_paths: V0/agent_memory_server/working_memory.py, V0/agent_memory_server/working_memory_index.py, V0/agent_memory_server/long_term_memory.py, V0/agent_memory_server/memory_strategies.py, V0/agent_memory_server/extraction.py
- **Clients, APIs, MCP, and Workbench**: importance `high`
  - source_paths: V0/agent_memory_server/mcp.py, V0/agent_memory_server/cli.py, V0/agent_memory_server/auth.py, V0/agent-memory-client/agent_memory_client/client.py, V0/agent-memory-client/agent_memory_client/models.py
- **Operations, Deployment, LLM/Embedding Integration, and Extensibility**: importance `high`
  - source_paths: V0/agent_memory_server/config.py, V0/agent_memory_server/dependencies.py, V0/agent_memory_server/memory_vector_db.py, V0/agent_memory_server/memory_vector_db_factory.py, V0/agent_memory_server/migrations.py

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `886437963dc02289e828872f0ae21fdaa734c337`
- inspected_files: `README.md`

Host AI hard rules:
- Without repo_clone_verified=true, do not claim that the source code has been read.
- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.
- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.

## Doramagic Pitfall Constraints

These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.

### Constraint 1: Capability evidence risk requires verification

- Trigger: README/documentation is current enough for a first validation pass.
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: capability.assumptions | https://github.com/redis/agent-memory-server
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 2: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: downstream_validation.risk_items | https://github.com/redis/agent-memory-server
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 3: Security or permission risk requires verification

- Trigger: no_demo
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: risks.scoring_risks | https://github.com/redis/agent-memory-server
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 4: Maintenance risk requires verification

- Trigger: issue_or_pr_quality=unknown。
- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.
- Why it matters: May increase setup, validation, or first-run risk for the user.
- Evidence: evidence.maintainer_signals | https://github.com/redis/agent-memory-server
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.