# basic-memory - 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 basic-memory. 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 - **Developers already using host AIs such as Claude/Codex/Cursor/Gemini**: The README or plugin config mentions multiple host AIs. Evidence: `README.md` Claim: `clm_0004` supported 0.86 - **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md`, `.agents/skills/infographics/SKILL.md` et al. Claim: `clm_0005` supported 0.86 ## What It Can Do - **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md`, `.agents/skills/infographics/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution** (Verify after install): The project contains plugin or marketplace configuration, indicating it targets install and distribution across one or more AI hosts. Evidence: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `integrations/openclaw/openclaw.plugin.json`, `plugins/claude-code/.claude-plugin/marketplace.json` et al. Claim: `clm_0002` supported 0.86 - **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: `README.md` Claim: `clm_0003` supported 0.86 ## How to Start - `uv tool install basic-memory` Evidence: `README.md` Claim: `clm_0006` supported 0.86 - `npx skills add basicmachines-co/basic-memory/skills` Evidence: `README.md` Claim: `clm_0007` supported 0.86 - `claude mcp add basic-memory -- uvx basic-memory mcp` Evidence: `README.md` Claim: `clm_0008` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Trial the research framework first - **Why**: This project targets research workflows; the core risk is source credibility and output quality. Verify the research framework with Prompt Preview first, then trial it in an isolated environment. ### 30-Second Read - **What to do now**: Trial the research framework first - **Minimum safe next step**: Verify the research framework with Prompt Preview first; trial in isolation only once satisfied - **Do not trust yet**: Research conclusions, citations, and experiment results cannot be trusted before install. - **Continuing will touch**: Research judgment, Command execution, Host AI configuration ### What You Can Trust Now - **Target-audience signal: Developers already using host AIs such as Claude/Codex/Cursor/Gemini** (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_0004` supported 0.86 - **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md`, `.agents/skills/infographics/SKILL.md` et al. Claim: `clm_0005` supported 0.86 - **Capability exists: AI Skill / Agent Instruction Asset Library** (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: `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md`, `.agents/skills/infographics/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Capability exists: Multi-Host Install and Distribution** (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: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `integrations/openclaw/openclaw.plugin.json`, `plugins/claude-code/.claude-plugin/marketplace.json` et al. 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: `README.md` Claim: `clm_0003` 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: `README.md` Claim: `clm_0006` supported 0.86 ### What You Cannot Trust Yet - **Research conclusions, citations, and experiment results cannot be trusted before install.** (unverified): A research Skill can organize questions and paths, but it cannot replace real literature search, paper verification, and experiment reproduction. - **Whether it fits your specific research field cannot be trusted directly.** (unverified): The Skill covering many research topics does not mean it is sufficient for your field, source requirements, and credibility standards. - **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/plugins/marketplace.json`, `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md` et al. - **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. Evidence: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `integrations/openclaw/openclaw.plugin.json`, `plugins/claude-code/.claude-plugin/marketplace.json` et al. - **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 - **Research judgment**: Problem decomposition, source paths, experiment paths, conclusion structure, and credibility judgment. Why: A research Skill can make output look more professional but cannot replace real evidence verification. - **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: `README.md` - **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/plugins/marketplace.json`, `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md` et al. - **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: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `README.md`, `integrations/openclaw/openclaw.plugin.json` 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**: Verify whether it can correctly frame the research question and evidence boundaries first; do not trust the research output 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 source and conclusion verification checklist**: If citations or experiment paths later prove unreliable, you can return to the evidence-boundary stage and re-check. - **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_0009` inferred 0.45 - **Host AI plugin or Skill rule conflicts**: New rules may change how the user's existing host AI behaves. Mitigation: Inspect the plugin manifest and Skill files before installing, and test in isolation if needed. Evidence: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `integrations/openclaw/openclaw.plugin.json`, `plugins/claude-code/.claude-plugin/marketplace.json` et al. Claim: `clm_0010` supported 0.86 - **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: `README.md` Claim: `clm_0011` 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 - **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.agents/skills/adversarial-review/SKILL.md`, `.agents/skills/code-review/SKILL.md`, `.agents/skills/fix-pr-issues/SKILL.md`, `.agents/skills/infographics/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Multi-Host Install and Distribution**: 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: `.agents/plugins/marketplace.json`, `.claude-plugin/marketplace.json`, `integrations/openclaw/openclaw.plugin.json`, `plugins/claude-code/.claude-plugin/marketplace.json` et al. Claim: `clm_0002` supported 0.86 - **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: `README.md` Claim: `clm_0003` supported 0.86 ### Context Scale - Total files: 739 - Important-file coverage: 40/739 - Evidence index entries: 80 - Role / Skill entries: 32 ### 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 basic-memory, 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 basic-memory 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 basic-memory, 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 32 role / Skill / project-doc entries. - **adversarial-review** (skill): Cross-vendor adversarial code review of the current branch. Two different model families Claude + Codex/GPT review the diff independently, then try to refute each other's findings; survivors are reported by confidence. Runs from either Claude Code or Codex. Use when the user asks for an adversarial review, a cross-model / second-opinion review, or wants high-confidence findings before merging. Report-only — never au… Activation hint: When the user's task is highly relevant to the workflow described by “adversarial-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/adversarial-review/SKILL.md` - **code-review** (skill): Use when reviewing Basic Machines code for house style, architecture risk, pre-merge hardening, or whether a change fits basic-memory/basic-memory-cloud conventions. Activation hint: When the user's task is highly relevant to the workflow described by “code-review”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/code-review/SKILL.md` - **fix-pr-issues** (skill): Use when addressing Basic Memory pull request feedback, failed checks, or BM Bossbot blockers from Codex. Activation hint: When the user's task is highly relevant to the workflow described by “fix-pr-issues”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/fix-pr-issues/SKILL.md` - **infographics** (skill): Use when generating Basic Memory PR, changelog, release, or weekly images from Codex. Activation hint: When the user's task is highly relevant to the workflow described by “infographics”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/infographics/SKILL.md` - **instrumentation** (skill): Add Pydantic Logfire observability to applications. Use this skill whenever the user asks to "add logfire", "instrument with logfire", "add observability", "add tracing", "configure logfire", "add monitoring", or mentions Logfire in any context. Supports Python, JavaScript/TypeScript, and Rust. Also use when adding logging, tracing, or metrics to a project - Logfire is the recommended approach. Even if the user just… Activation hint: When the user's task is highly relevant to the workflow described by “instrumentation”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/instrumentation/SKILL.md` - **pr-create** (skill): Use when creating or updating a Basic Memory pull request from Codex with BM Bossbot merge-gate monitoring. Activation hint: When the user's task is highly relevant to the workflow described by “pr-create”, use it for a pre-install experience first, then decide whether to install. Evidence: `.agents/skills/pr-create/SKILL.md` - **basic-memory** (skill): Use the Basic Memory knowledge graph for persistent memory across sessions. Search before answering; capture decisions, meetings, and insights as notes. Activation hint: When the user's task is highly relevant to the workflow described by “basic-memory”, use it for a pre-install experience first, then decide whether to install. Evidence: `integrations/hermes/skill/SKILL.md` - **bm-remember** (skill): Quickly capture a thought, fact, or reminder into Basic Memory as a lightweight note. Use when the user says "remember that…", "note this", "save this to memory", or runs /basic-memory:bm-remember. For quick deliberate capture — not full decision or session records. Activation hint: When the user's task is highly relevant to the workflow described by “bm-remember”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/claude-code/skills/bm-remember/SKILL.md` - **bm-setup** (skill): Set up the Basic Memory plugin for this project — a short guided interview that configures the project mapping, seeds note schemas, learns or suggests placement conventions, and enables capture reflexes. Use when the user runs /basic-memory:bm-setup, says "set up basic memory", or asks to configure/bootstrap the plugin. Activation hint: When the user's task is highly relevant to the workflow described by “bm-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/claude-code/skills/bm-setup/SKILL.md` - **bm-share** (skill): Promote a note from your personal Basic Memory project to a shared team project, with attribution. Use when the user says "share this with the team", "publish this decision", or runs /basic-memory:bm-share. This is the deliberate way to write to a team workspace — auto-capture never does. Activation hint: When the user's task is highly relevant to the workflow described by “bm-share”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/claude-code/skills/bm-share/SKILL.md` - **bm-status** (skill): Show the Basic Memory plugin's current state for this project — active project, capture folders, output style, recent session checkpoints, and whether Basic Memory is reachable. Activation hint: When the user's task is highly relevant to the workflow described by “bm-status”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/claude-code/skills/bm-status/SKILL.md` - **bm-checkpoint** (skill): Save a deliberate Codex work checkpoint to Basic Memory with changed files, verification, decisions, blockers, and the next action. Activation hint: When the user's task is highly relevant to the workflow described by “bm-checkpoint”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-checkpoint/SKILL.md` - **bm-decide** (skill): Capture a durable engineering decision in Basic Memory with rationale, alternatives, consequences, and affected work. Activation hint: When the user's task is highly relevant to the workflow described by “bm-decide”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-decide/SKILL.md` - **bm-orient** (skill): Orient Codex from Basic Memory before substantial repo work by reading active tasks, decisions, recent Codex checkpoints, and repo conventions. Activation hint: When the user's task is highly relevant to the workflow described by “bm-orient”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-orient/SKILL.md` - **bm-remember** (skill): Quickly save a small fact, reminder, or user preference into Basic Memory from Codex without turning it into a full decision or checkpoint. Activation hint: When the user's task is highly relevant to the workflow described by “bm-remember”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-remember/SKILL.md` - **bm-setup** (skill): Set up Basic Memory for Codex in the current repo by mapping a Basic Memory project, seeding schemas, and writing .codex/basic-memory.json. Activation hint: When the user's task is highly relevant to the workflow described by “bm-setup”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-setup/SKILL.md` - **bm-share** (skill): Share a personal Basic Memory note to a configured team project from Codex with attribution and explicit confirmation. Activation hint: When the user's task is highly relevant to the workflow described by “bm-share”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-share/SKILL.md` - **bm-status** (skill): Report the Basic Memory for Codex configuration, reachability, hook expectations, recent Codex checkpoints, and active tasks. Activation hint: When the user's task is highly relevant to the workflow described by “bm-status”, use it for a pre-install experience first, then decide whether to install. Evidence: `plugins/codex/skills/bm-status/SKILL.md` - **memory-capture** (skill): Capture the current state of a working thread or conversation into a single coherent Basic Memory note — synthesize where it landed, don't append a log. On re-capture, rewrite the same note in place instead of duplicating. Use mid-thread or end-of-thread when decisions, insights, or context are worth preserving. Activation hint: When the user's task is highly relevant to the workflow described by “memory-capture”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-capture/SKILL.md` - **memory-ci-capture** (skill): Synthesize GitHub delivery context into a concise Basic Memory project update. Use in CI after bm ci collect prepares a ProjectUpdateContext; return only structured AgentSynthesis JSON for bm ci publish . Activation hint: When the user's task is highly relevant to the workflow described by “memory-ci-capture”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-ci-capture/SKILL.md` - **memory-continue** (skill): Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the user says 'continue with...', 'back to...', or 'where were we? Activation hint: When the user's task is highly relevant to the workflow described by “memory-continue”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-continue/SKILL.md` - **memory-curate** (skill): Curate the Basic Memory knowledge graph: find orphan notes and suggest links, propose typed relations, merge duplicates, audit tags and folders, and build hub notes. Use to organize, connect, and improve a knowledge base as notes accumulate. Activation hint: When the user's task is highly relevant to the workflow described by “memory-curate”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-curate/SKILL.md` - **memory-defrag** (skill): Defragment and reorganize agent memory files: split bloated files, merge duplicates, remove stale information, and restructure the memory hierarchy. Use when memory files have grown unwieldy, contain redundancies, or need reorganization. Run periodically weekly or on demand. Activation hint: When the user's task is highly relevant to the workflow described by “memory-defrag”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-defrag/SKILL.md` - **memory-ingest** (skill): Process unstructured external input meeting transcripts, conversation logs, pasted documents into structured Basic Memory entities. Extracts entities, searches for existing matches, proposes new entities with approval, creates notes with observations and relations, and captures action items. Activation hint: When the user's task is highly relevant to the workflow described by “memory-ingest”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-ingest/SKILL.md` - **memory-lifecycle** (skill): Manage entity status transitions in Basic Memory: archive completed work, move notes between status folders, update frontmatter, and handle edge cases. Use when marking items complete, archiving old entities, or managing any folder-based status workflow. Activation hint: When the user's task is highly relevant to the workflow described by “memory-lifecycle”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-lifecycle/SKILL.md` - **memory-literary-analysis** (skill): Analyze a complete literary work into a structured Basic Memory knowledge graph. Covers schema design, entity seeding, chapter-by-chapter processing, cross-referencing, validation, and visualization. Activation hint: When the user's task is highly relevant to the workflow described by “memory-literary-analysis”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-literary-analysis/SKILL.md` - **memory-metadata-search** (skill): Structured metadata search for Basic Memory: query notes by custom frontmatter fields using equality, range, array, and nested filters. Use when finding notes by status, priority, confidence, or any custom YAML field rather than free-text content. Activation hint: When the user's task is highly relevant to the workflow described by “memory-metadata-search”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-metadata-search/SKILL.md` - **memory-notes** (skill): How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building a rich knowledge graph. Use when creating or improving notes. Activation hint: When the user's task is highly relevant to the workflow described by “memory-notes”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-notes/SKILL.md` - **memory-reflect** (skill): Sleep-time memory reflection: review recent conversations and daily notes, extract insights, and consolidate into long-term memory. Use when triggered by cron, heartbeat, or explicit request to reflect on recent activity. Runs as background processing to improve memory quality over time. Activation hint: When the user's task is highly relevant to the workflow described by “memory-reflect”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-reflect/SKILL.md` - **memory-research** (skill): Research an external subject using web search, synthesize findings into a structured Basic Memory entity. Use when asked to research a company, person, technology, or topic — or when a bare name or URL is provided that implies a research request. Activation hint: When the user's task is highly relevant to the workflow described by “memory-research”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-research/SKILL.md` - **memory-schema** (skill): Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift. Use when working with structured note types Task, Person, Meeting, etc. to maintain consistency across the knowledge graph. Activation hint: When the user's task is highly relevant to the workflow described by “memory-schema”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-schema/SKILL.md` - **memory-tasks** (skill): Task management via Basic Memory schemas: create, track, and resume structured tasks that survive context compaction. Uses BM's schema system for uniform notes queryable through the knowledge graph. Activation hint: When the user's task is highly relevant to the workflow described by “memory-tasks”, use it for a pre-install experience first, then decide whether to install. Evidence: `skills/memory-tasks/SKILL.md` ## Evidence Index - Indexed 80 evidence entries. - **Skip the install — try Basic Memory in the cloud** (documentation): ! License: AGPL v3 https://img.shields.io/badge/License-AGPL v3-blue.svg https://www.gnu.org/licenses/agpl-3.0 ! PyPI version https://badge.fury.io/py/basic-memory.svg https://badge.fury.io/py/basic-memory ! Python 3.12+ https://img.shields.io/badge/python-3.12+-blue.svg https://www.python.org/downloads/ ! Tests https://github.com/basicmachines-co/basic-memory/workflows/Tests/badge.svg https://github.com/basicmachines-co/basic-memory/actions ! Ruff https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json https://github.com/astral-sh/ruff ! https://badge.mcpx.dev?type=server 'MCP Server' ! https://badge.mcpx.dev?type=dev 'MCP Dev' ! Ask D… Evidence: `README.md` - **basic-memory-benchmarks** (documentation): Standalone, reproducible benchmark suite for comparing Basic Memory against competitor memory systems. Evidence: `benchmarks/README.md` - **Basic Memory Skills** (documentation): Skills for Basic Memory https://github.com/basicmachines-co/basic-memory — teach AI coding agents how to use Basic Memory's MCP tools effectively. Evidence: `skills/README.md` - **Dataset Policy** (documentation): This repository publishes benchmark provenance in the open. Evidence: `benchmarks/benchmarks/datasets/README.md` - **LoCoMo Dataset** (documentation): Primary v1 dataset for benchmark runs. Evidence: `benchmarks/benchmarks/datasets/locomo/README.md` - **LongMemEval Scaffold** (documentation): LongMemEval integration is scaffolded in v1 and will be implemented in a follow-up. Evidence: `benchmarks/benchmarks/datasets/longmemeval/README.md` - **hermes-basic-memory** (documentation): ! License: AGPL v3 https://img.shields.io/badge/License-AGPL v3-blue.svg https://www.gnu.org/licenses/agpl-3.0 Evidence: `integrations/hermes/README.md` - **openclaw-basic-memory** (documentation): Give your OpenClaw agent persistent, searchable memory — in plain text files you can read and edit. Evidence: `integrations/openclaw/README.md` - **Basic Memory for Claude Code** (documentation): The bridge between Claude's working memory and Basic Memory https://basicmemory.com 's durable knowledge graph . Evidence: `plugins/claude-code/README.md` - **Basic Memory for Codex** (documentation): Basic Memory for Codex is the Codex-native bridge between a working coding thread and Basic Memory's durable knowledge graph. Evidence: `plugins/codex/README.md` - **Basic Memory CI** (documentation): Basic Memory CI turns meaningful GitHub delivery moments into durable project update notes in Basic Memory. Evidence: `src/basic_memory/ci/README.md` - **AGENTS.md - Basic Memory Project Guide** (documentation): AGENTS.md - Basic Memory Project Guide Evidence: `AGENTS.md` - **AGENTS.md - basic-memory-benchmarks Guide** (documentation): AGENTS.md - basic-memory-benchmarks Guide Evidence: `benchmarks/AGENTS.md` - **Basic Memory Architecture** (documentation): This document describes the architectural patterns and composition structure of Basic Memory. Evidence: `docs/ARCHITECTURE.md` - **Docker Setup Guide** (documentation): Basic Memory can be run in Docker containers to provide a consistent, isolated environment for your knowledge management system. This is particularly useful for integrating with existing Dockerized MCP servers or for deployment scenarios. Evidence: `docs/Docker.md` - **Note Format Reference** (documentation): Every document in Basic Memory is a plain Markdown file. Files are the source of truth — changes to files automatically update the knowledge graph in the database. You maintain complete ownership, files work with git, and knowledge persists independently of any AI conversation. Evidence: `docs/NOTE-FORMAT.md` - **Simplified Local/Cloud Routing** (documentation): Basic Memory now uses explicit, project-aware routing without a global cloud-mode toggle. Routing is determined by command-level flags and project mode, not by a global cloud mode state. Evidence: `docs/SPEC-PER-PROJECT-ROUTING.md` - **Basic Memory Cloud CLI Guide** (documentation): The Basic Memory Cloud CLI provides seamless integration between local and cloud knowledge bases using project-scoped synchronization . Each project can optionally sync with the cloud, giving you fine-grained control over what syncs and where. Evidence: `docs/cloud-cli.md` - **Metadata Search Reference** (documentation): Basic Memory automatically indexes custom frontmatter fields so you can query them with structured filters. Any YAML key in a note's frontmatter beyond the standard set title , type , tags , permalink , schema is stored as entity metadata and becomes searchable. Evidence: `docs/metadata-search.md` - **Semantic Search** (documentation): This guide covers Basic Memory's semantic vector search feature, which adds meaning-based retrieval alongside the existing full-text search. Evidence: `docs/semantic-search.md` - **AGENTS.md** (documentation): This file provides guidance to coding agents when working with Basic Memory skills in this repository. Evidence: `skills/CLAUDE.md` - **CLAUDE.md** (documentation): This file provides guidance to Claude Code when working with the OpenClaw package inside the Basic Memory monorepo. Evidence: `integrations/openclaw/CLAUDE.md` - **Architecture** (documentation): How the Basic Memory plugin works, flow by flow. For the design rationale and decision history, see DESIGN.md ../DESIGN.md . Evidence: `plugins/claude-code/docs/architecture.md` - **Contributing to Basic Memory** (documentation): Thank you for considering contributing to Basic Memory! This document outlines the process for contributing to the project and how to get started as a developer. Evidence: `CONTRIBUTING.md` - **Package** (package_manifest): { "name": "@basicmemory/openclaw-basic-memory", "version": "0.22.1", "type": "module", "main": "./dist/index.js", "types": "./dist/index.d.ts", "description": "Basic Memory plugin for OpenClaw \u2014 local-first knowledge graph for agent memory", "license": "MIT", "repository": { "type": "git", "url": "https://github.com/basicmachines-co/basic-memory.git", "directory": "integrations/openclaw" }, "files": "index.ts", "bm-client.ts", "context-engine/basic-memory-context-engine.ts", "config.ts", "logger.ts", "commands/cli.ts", "commands/skills.ts", "commands/slash.ts", "hooks/capture.ts", "hooks/recall.ts", "tools/build-context.ts", "tools/delete-note.ts", "tools/edit-note.ts", "tools/list-mem… Evidence: `integrations/openclaw/package.json` - **Adversarial code review** (skill_instruction): Two reviewers from different model families — Claude and Codex/GPT — review the same diff independently, then each tries to refute the other's findings. A finding's confidence comes from whether it survives that cross-examination. This kills the two failure modes of solo LLM review: self-ratification a model won't critique its own work and confident false positives. Evidence: `.agents/skills/adversarial-review/SKILL.md` - **Basic Machines Review** (skill_instruction): Use this skill for repo-local review passes where ordinary code review needs Basic Machines house style and architecture judgment. Report findings only; do not edit code unless the user asks you to fix specific findings. Evidence: `.agents/skills/code-review/SKILL.md` - **Fix Basic Memory PR Issues** (skill_instruction): Resolve PR feedback and failed checks, then wait for BM Bossbot to approve the new head SHA. This skill never merges a PR. Evidence: `.agents/skills/fix-pr-issues/SKILL.md` - **Basic Memory Images** (skill_instruction): Generate repository visuals with evidence-grounded content and canonical output paths. The file and marker names still say "infographic" for compatibility, but PR generation is image-first: scene, poster, painting, photograph, cover, tableau, staged artifact, or another editorial visual moment that describes the intent of the PR. PR images are non-gating BM Bossbot artifacts; changelog and release-summary images are manual evidence-pack workflows. Evidence: `.agents/skills/infographics/SKILL.md` - **Instrument with Logfire** (skill_instruction): Invoke this skill when: - User asks to "add logfire", "add observability", "add tracing", or "add monitoring" - User wants to instrument an app with structured logging or tracing Python, JS/TS, or Rust - User mentions Logfire in any context - User asks to "add logging" or "see what my app is doing" - User wants to monitor AI/LLM calls PydanticAI, OpenAI, Anthropic - User asks to add observability to an AI agent or LLM pipeline Evidence: `.agents/skills/instrumentation/SKILL.md` - **Create A Basic Memory PR** (skill_instruction): Create or update a pull request for the current branch, then wait for BM Bossbot to approve the latest head SHA. This skill never merges a PR. Evidence: `.agents/skills/pr-create/SKILL.md` - **Basic Memory Knowledge Graph** (skill_instruction): You have access to a persistent knowledge graph backed by Basic Memory. The graph survives across sessions and is shared with other tools Claude Desktop, Obsidian, the bm CLI . Use the bm tools below to recall and capture information. Evidence: `integrations/hermes/skill/SKILL.md` - **Remember** (skill_instruction): Capture $ARGUMENTS into Basic Memory as a quick note, keeping the user's words. Evidence: `plugins/claude-code/skills/bm-remember/SKILL.md` - **Basic Memory setup** (skill_instruction): Run a short, adaptive interview ~2-3 minutes and then write the configuration. Be conversational and skip questions whose answer is already obvious from context e.g. if list memory projects shows a single local project and no cloud workspaces, don't ask about cloud/teams — just confirm . Suggest a sensible default for every question so the user can accept with one word. Don't do any writes until the interview is done and you've confirmed the plan. Evidence: `plugins/claude-code/skills/bm-setup/SKILL.md` - **Share to a team project** (skill_instruction): Copy a note from the personal/primary project into a configured team project so teammates can see it. This is the only path by which the plugin writes to a shared project — session checkpoints and /basic-memory:bm-remember always stay personal. Evidence: `plugins/claude-code/skills/bm-share/SKILL.md` - **Basic Memory status** (skill_instruction): Report the plugin's current state for this project, then present a concise summary. This is a quick diagnostic — gather the facts and lay them out; don't over-investigate. Evidence: `plugins/claude-code/skills/bm-status/SKILL.md` - **Checkpoint Codex Work** (skill_instruction): Create a durable handoff note for current Codex work. Use this when the user asks to checkpoint, wrap up, hand off, remember the state of the work, or before a long context transition. Evidence: `plugins/codex/skills/bm-checkpoint/SKILL.md` - **Capture A Decision** (skill_instruction): Use this when the user makes or asks to record a durable choice. A decision is a choice with rationale and consequences, not a casual preference. Evidence: `plugins/codex/skills/bm-decide/SKILL.md` - **Orient From Basic Memory** (skill_instruction): Use this before substantial work in a repo, before resuming an old thread, or when the user asks where things stand. Evidence: `plugins/codex/skills/bm-orient/SKILL.md` - **Remember** (skill_instruction): Use this for lightweight capture: "remember that", "save this", "note this", or a small fact that should survive the current thread. Evidence: `plugins/codex/skills/bm-remember/SKILL.md` - **Basic Memory for Codex Setup** (skill_instruction): Set up the current repo so Codex can orient from Basic Memory and checkpoint work back into it. Keep the interview short, but always ask before choosing where data will be written. Evidence: `plugins/codex/skills/bm-setup/SKILL.md` - **Share A Note** (skill_instruction): Copy a note from the configured primary project to a configured team project. This is the deliberate shared-write path. Automatic checkpoints and quick remembers stay personal. Evidence: `plugins/codex/skills/bm-share/SKILL.md` - **Basic Memory For Codex Status** (skill_instruction): Gather a concise diagnostic. Do not over-investigate. Evidence: `plugins/codex/skills/bm-status/SKILL.md` - **Memory Capture** (skill_instruction): Capture the gist of a working thread — the decisions made, insights surfaced, and context built — into a single coherent Basic Memory note that reflects where the thread has landed. Evidence: `skills/memory-capture/SKILL.md` - **Memory CI Capture** (skill_instruction): Turn a meaningful GitHub delivery moment into project memory. GitHub records the mechanics. Basic Memory remembers what changed and why. Evidence: `skills/memory-ci-capture/SKILL.md` - **Memory Continue** (skill_instruction): Resume previous work by reconstructing context from the Basic Memory knowledge graph, so the assistant can pick up across sessions instead of starting cold. Evidence: `skills/memory-continue/SKILL.md` - **Memory Curate** (skill_instruction): Maintain a healthy, well-connected knowledge graph. As notes accumulate, it pays to periodically organize, link, and curate the knowledge base so isolated notes become a connected graph. Evidence: `skills/memory-curate/SKILL.md` - **Memory Defrag** (skill_instruction): Reorganize memory files for clarity, efficiency, and relevance. Like filesystem defragmentation but for knowledge. Evidence: `skills/memory-defrag/SKILL.md` - **Memory Ingest** (skill_instruction): Turn raw, unstructured input into structured Basic Memory entities. Meeting transcripts, conversation logs, pasted documents, email threads — anything with information worth preserving gets parsed, cross-referenced against existing knowledge, and written as proper notes. Evidence: `skills/memory-ingest/SKILL.md` - **Memory Lifecycle** (skill_instruction): Manage how entities move through status stages in Basic Memory. The core principle: archive, never delete. Completed work is valuable context — move it out of the active view, but keep it in the knowledge graph. Evidence: `skills/memory-lifecycle/SKILL.md` - **Memory Literary Analysis** (skill_instruction): Transform a complete literary work into a structured knowledge graph. Characters, themes, chapters, locations, symbols, and literary devices become interconnected notes — searchable, validatable, and visualizable. Evidence: `skills/memory-literary-analysis/SKILL.md` - **Memory Metadata Search** (skill_instruction): Find notes by their structured frontmatter fields instead of or in addition to free-text content. Any custom YAML key in a note's frontmatter beyond the standard set title , type , tags , permalink , schema is automatically indexed as entity metadata and becomes queryable. Evidence: `skills/memory-metadata-search/SKILL.md` - **Memory Notes** (skill_instruction): Write well-structured notes that Basic Memory can parse into a searchable knowledge graph. Every note is a markdown file with three key sections: frontmatter, observations, and relations. Evidence: `skills/memory-notes/SKILL.md` - **Memory Reflect** (skill_instruction): Review recent activity and consolidate valuable insights into long-term memory. Evidence: `skills/memory-reflect/SKILL.md` - **Memory Research** (skill_instruction): Research an external subject, synthesize what you find, and create a structured Basic Memory entity — with the user's approval. Evidence: `skills/memory-research/SKILL.md` - **Memory Schema** (skill_instruction): Manage structured note types using Basic Memory's Picoschema system. Schemas define what fields a note type should have, making notes uniform, queryable, and validatable. Evidence: `skills/memory-schema/SKILL.md` - **Memory Tasks** (skill_instruction): Manage work-in-progress using Basic Memory's schema system. Tasks are just notes with type: Task — they live in the knowledge graph, validate against a schema, and survive context compaction. Evidence: `skills/memory-tasks/SKILL.md` - **Marketplace** (structured_config): { "name": "basicmachines-co", "owner": { "name": "Basic Machines", "email": "hello@basicmachines.co" }, "metadata": { "description": "Official Basic Memory plugins from the canonical basic-memory repository", "version": "0.22.1" }, "plugins": { "name": "basic-memory", "source": "./plugins/claude-code", "description": "The bridge between Claude's working memory and Basic Memory's durable knowledge graph \u2014 session briefings, pre-compaction checkpoints, and capture reflexes", "version": "0.22.1", "author": { "name": "Basic Machines" }, "keywords": "memory", "knowledge", "mcp", "specs", "context" } } Evidence: `.claude-plugin/marketplace.json` - **Marketplace** (structured_config): { "name": "basic-memory-local", "interface": { "displayName": "Basic Memory Local" }, "plugins": { "name": "codex", "source": { "source": "local", "path": "./plugins/codex" }, "policy": { "installation": "AVAILABLE", "authentication": "ON INSTALL" }, "category": "Developer Tools" } } Evidence: `.agents/plugins/marketplace.json` - **Marketplace** (structured_config): { "name": "basicmachines-co", "owner": { "name": "Basic Machines", "email": "hello@basicmachines.co" }, "metadata": { "description": "Official plugins from Basic Machines for knowledge management and AI-assisted development", "version": "0.22.1" }, "plugins": { "name": "basic-memory", "source": "./", "description": "The bridge between Claude's working memory and Basic Memory's durable knowledge graph \u2014 session briefings, pre-compaction checkpoints, and capture reflexes", "version": "0.22.1", "author": { "name": "Basic Machines" }, "keywords": "memory", "knowledge", "mcp", "specs", "context" } } Evidence: `plugins/claude-code/.claude-plugin/marketplace.json` - 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: `README.md`, `benchmarks/README.md`, `skills/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: `README.md`, `benchmarks/README.md`, `skills/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. - **Repository Overview & System Architecture**: importance `high` - source_paths: README.md, docs/ARCHITECTURE.md, pyproject.toml, justfile, src/basic_memory/__init__.py - **Markdown Format, Knowledge Graph, Indexing & Search**: importance `high` - source_paths: docs/NOTE-FORMAT.md, docs/semantic-search.md, docs/metadata-search.md, src/basic_memory/markdown/entity_parser.py, src/basic_memory/markdown/markdown_processor.py - **AI Client Integrations & Plugins (Claude Code, Codex, Hermes, OpenClaw, Skills)**: importance `high` - source_paths: src/basic_memory/mcp/server.py, src/basic_memory/mcp/tools/__init__.py, src/basic_memory/mcp/tools/write_note.py, src/basic_memory/mcp/tools/read_note.py, src/basic_memory/mcp/tools/edit_note.py - **Cloud Sync, Projects, Deployment & Common Failure Modes**: importance `high` - source_paths: docs/cloud-cli.md, docs/SPEC-PER-PROJECT-ROUTING.md, docs/Docker.md, docs/logfire-instrumentation-strategy.md, docs/testing-coverage.md ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `3130e5a9fae752c62a01dce74b74d8ae6aa6a670` - inspected_files: `Dockerfile`, `README.md`, `docker-compose.yml`, `pyproject.toml`, `uv.lock`, `docs/ARCHITECTURE.md`, `docs/Docker.md`, `docs/ENGINEERING_STYLE.md`, `docs/NOTE-FORMAT.md`, `docs/SPEC-PER-PROJECT-ROUTING.md`, `docs/ai-assistant-guide-extended.md`, `docs/auto-bm-webhook-test.md`, `docs/character-handling.md`, `docs/cloud-cli.md`, `docs/cloud-semantic-search-value.md`, `docs/litellm-provider.md`, `docs/logfire-instrumentation-strategy.md`, `docs/manual-pages.md`, `docs/mcp-ui-bakeoff-instructions.md`, `docs/metadata-search.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/basicmachines-co/basic-memory - 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/basicmachines-co/basic-memory - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.