# kimetsu - 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 kimetsu. 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_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: `README.md`, `docs/INSTALL.md` Claim: `clm_0001` supported 0.86

## How to Start

- `npm install -g kimetsu-ai` Evidence: `README.md` Claim: `clm_0003` supported 0.86, `clm_0004` supported 0.86
- `npm install -g kimetsu-ai          # lean build (all host integrations included)` Evidence: `docs/INSTALL.md` Claim: `clm_0004` supported 0.86

## Continue-or-Stop Decision Card

- **Current recommendation**: Needs admin / security approval
- **Why**: Continuing may involve secrets, accounts, external services, or sensitive context; get admin or security approval first.

### 30-Second Read

- **What to do now**: Needs admin / security approval
- **Minimum safe next step**: Run Prompt Preview first; if credentials or an enterprise environment are involved, get approval before trialing
- **Do not trust yet**: Role quality and task fit cannot be trusted directly.
- **Continuing will touch**: Role selection bias, Command execution, Local environment or project files

### 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_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`, `docs/INSTALL.md` 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: `README.md` Claim: `clm_0003` supported 0.86, `clm_0004` 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.
- **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: `README.md`, `docs/INSTALL.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: `README.md`, `docs/INSTALL.md`
- **Environment variables / API keys**: Project entry docs explicitly showing API key, token, secret, or account credential configuration. Why: If a real install needs credentials, use test credentials first and go through a permission/compliance review. Evidence: `CHANGELOG.md`, `docs/INSTALL.md`, `docs/how-kimetsu-works/configuration.md`
- **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.)
- **Do not use real production credentials**: Once an environment variable / API key enters the host or toolchain, it can create account and compliance risk. (applies when: When environment signals like API, TOKEN, KEY, or SECRET appear.)
- **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.
- **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.
- **Be ready to revoke test API keys or tokens**: If test credentials leak or are misused, you can cut losses quickly.
- **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_0005` 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: `README.md`, `docs/INSTALL.md` Claim: `clm_0006` 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: `README.md`, `docs/INSTALL.md` Claim: `clm_0001` supported 0.86

### Context Scale

- Total files: 201
- Important-file coverage: 40/201
- Evidence index entries: 79
- Role / Skill entries: 26

### 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 kimetsu, 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 kimetsu 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 kimetsu, 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 26 role / Skill / project-doc entries.

- **Kimetsu** (project_doc): Give your coding agent a memory that gets sharper every run. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `README.md`
- **npm distribution** (project_doc): Kimetsu is also published to npm as the kimetsu-ai package the kimetsu package name was taken; the project's npm scope is @kimetsu-ai , so JS/TS users can npm install -g kimetsu-ai without a Rust toolchain. npm ships the same prebuilt native binary as the GitHub Release — it is not a reimplementation. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `npm/README.md`
- **website-fumadocs** (project_doc): This is a Next.js application generated with Create Fumadocs https://github.com/fuma-nama/fumadocs . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `website-fumadocs/README.md`
- **kimetsu-remote beta** (project_doc): Server-hosted Kimetsu brain over HTTP MCP — one brain per repository, shared from a server. This is a separate package from the kimetsu-ai CLI: the remote server is intentionally not installed with kimetsu . Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `npm/kimetsu-remote/README.md`
- **kimetsu-ai** (project_doc): A persistent memory brain sidecar for Claude Code and Codex. It accumulates generalizable knowledge across sessions and retrieves it on demand. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `npm/kimetsu/README.md`
- **Contributing to kimetsu** (project_doc): Thanks for helping improve kimetsu. This repo keeps a clean, secure main and develop through automated checks at two points: locally on every commit, and in CI on every pull request. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/CONTRIBUTING.md`
- **Installing Kimetsu** (project_doc): Kimetsu is a single Rust binary. There's really only one choice to make at install time, lean vs semantic embeddings , because that's the only part baked into the binary. Which host agents you use Claude Code, Codex, Pi, OpenClaw is a runtime choice you change anytime with kimetsu plugin install / uninstall , with no reinstall. The official prebuilt + npm binaries include all six host integrations; a bare source car… Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/INSTALL.md`
- **Ways to use it** (project_doc): Kimetsu is a sidecar brain for coding agents. It runs alongside supported host agents through MCP including Claude Code and Codex , or as a standalone chat REPL. It watches what the model does, learns which memories actually help, and feeds higher-signal context into future runs. This document explains the moving parts, in the order you'll encounter them. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/index.md`
- **The headline numbers** (project_doc): Kimetsu's house rule is that every claim ships with a measurement. This section documents how we measure the brain and what the numbers are, so you can check them rather than take our word for it. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/index.md`
- **Contributor Covenant Code of Conduct** (project_doc): Contributor Covenant Code of Conduct Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/CODE_OF_CONDUCT.md`
- **Fully-local Kimetsu: zero external network calls** (project_doc): Fully-local Kimetsu: zero external network calls Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/LOCAL-MODELS.md`
- **Kimetsu Remote beta** (project_doc): Run the brain on a server and connect over HTTP MCP , so a team or you across machines shares one brain per repository, with no local checkout. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/REMOTE.md`
- **Kimetsu Algorithm** (project_doc): How Kimetsu turns memory into measurable savings: every cited memory is credited with the tokens it saved, every injection is charged for the tokens it cost, and kimetsu brain roi reports the net. This page documents the exact accounting so the ledger can be audited rather than trusted. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/ROI-METHODOLOGY.md`
- **Switching re-projects from the event log.** (project_doc): Every knob in project.toml , the off-switches, and the environment overrides. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/configuration.md`
- **The MCP surface** (project_doc): The MCP tool surface, the host hooks that make the loop reliable, and proactive mid-work recall. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/interfaces.md`
- **Citations + blame** (project_doc): Citations, decay, dedup, conflict detection, and the analytics that prove the brain is helping. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/learning-loop.md`
- **The bridge** (project_doc): The bridge, brain sharing, doctor, and what Kimetsu is not. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/operations.md`
- **Retrieval Models** (project_doc): Which embedder and reranker Kimetsu ships, why, and how to swap or re-benchmark them. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/retrieval-models.md`
- **Durable upgrades: schema migrations** (project_doc): brain.db: the event-sourced SQLite file that holds everything Kimetsu remembers, and how it migrates safely. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/the-brain.md`
- **Embeddings vs lean builds** (project_doc): How the broker scores, selects, and budgets the memories injected into each run. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/how-kimetsu-works/the-broker.md`
- **Results: 100K bucket** (project_doc): How Kimetsu scores on BEAM, the ten-ability long-term-memory benchmark, at the 100K and 1M token buckets. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/beam.md`
- **Brainbench** (project_doc): BrainBench is Kimetsu's own reader-free capability benchmark: it drives the real binary across difficulty tiers and scores dedup, forgetting, importance, and calibration with no LLM in the loop. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/brainbench.md`
- **How Kimetsu compares** (project_doc): How Kimetsu compares to mem0, Cognee, Zep, and Letta on the shared public benchmarks, and what we do not yet claim. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/comparison.md`
- **Results** (project_doc): How Kimetsu scores on LongMemEval, the public long-term-memory benchmark, with the exact setup so the number can be reproduced and compared. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/longmemeval.md`
- **Retrieval quality** (project_doc): Kimetsu's retrieval and correctness numbers: recall, MRR, latency, stale-hit suppression, and contradiction resolution, all reproducible from the shipped CLI. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `docs/memory-benchmark/retrieval-and-correctness.md`
- **Changelog** (project_doc): All notable changes to kimetsu land here. The format follows Keep a Changelog https://keepachangelog.com/en/1.1.0/ ; versions follow SemVer https://semver.org/spec/v2.0.0.html . From v1.0.0 onward the project follows SemVer normally: patch releases are bug-fix-only, minor releases are backward-compatible additions, and breaking changes require a major bump. Activation hint: Reference this when the user needs to understand the project's structure, install path, or boundaries. Evidence: `CHANGELOG.md`

## Evidence Index

- Indexed 79 evidence entries.

- **Kimetsu** (documentation): Give your coding agent a memory that gets sharper every run. Evidence: `README.md`
- **npm distribution** (documentation): Kimetsu is also published to npm as the kimetsu-ai package the kimetsu package name was taken; the project's npm scope is @kimetsu-ai , so JS/TS users can npm install -g kimetsu-ai without a Rust toolchain. npm ships the same prebuilt native binary as the GitHub Release — it is not a reimplementation. Evidence: `npm/README.md`
- **website-fumadocs** (documentation): This is a Next.js application generated with Create Fumadocs https://github.com/fuma-nama/fumadocs . Evidence: `website-fumadocs/README.md`
- **kimetsu-remote beta** (documentation): Server-hosted Kimetsu brain over HTTP MCP — one brain per repository, shared from a server. This is a separate package from the kimetsu-ai CLI: the remote server is intentionally not installed with kimetsu . Evidence: `npm/kimetsu-remote/README.md`
- **kimetsu-ai** (documentation): A persistent memory brain sidecar for Claude Code and Codex. It accumulates generalizable knowledge across sessions and retrieves it on demand. Evidence: `npm/kimetsu/README.md`
- **Contributing to kimetsu** (documentation): Thanks for helping improve kimetsu. This repo keeps a clean, secure main and develop through automated checks at two points: locally on every commit, and in CI on every pull request. Evidence: `docs/CONTRIBUTING.md`
- **Installing Kimetsu** (documentation): Kimetsu is a single Rust binary. There's really only one choice to make at install time, lean vs semantic embeddings , because that's the only part baked into the binary. Which host agents you use Claude Code, Codex, Pi, OpenClaw is a runtime choice you change anytime with kimetsu plugin install / uninstall , with no reinstall. The official prebuilt + npm binaries include all six host integrations; a bare source cargo install is minimal and adds them with --features pi,openclaw . Evidence: `docs/INSTALL.md`
- **Ways to use it** (documentation): Kimetsu is a sidecar brain for coding agents. It runs alongside supported host agents through MCP including Claude Code and Codex , or as a standalone chat REPL. It watches what the model does, learns which memories actually help, and feeds higher-signal context into future runs. This document explains the moving parts, in the order you'll encounter them. Evidence: `docs/how-kimetsu-works/index.md`
- **The headline numbers** (documentation): Kimetsu's house rule is that every claim ships with a measurement. This section documents how we measure the brain and what the numbers are, so you can check them rather than take our word for it. Evidence: `docs/memory-benchmark/index.md`
- **Package** (package_manifest): { "name": "website-fumadocs", "version": "0.0.0", "private": true, "scripts": { "sync-docs": "node scripts/sync-docs.mjs", "prebuild": "node scripts/sync-docs.mjs", "build": "next build", "postbuild": "node -e \"require 'fs' .writeFileSync 'out/.nojekyll','' ;require 'fs' .writeFileSync 'out/CNAME','kimetsu.dev' \"", "predev": "node scripts/sync-docs.mjs", "dev": "next dev", "start": "serve out", "types:check": "fumadocs-mdx && next typegen && tsc --noEmit", "postinstall": "fumadocs-mdx", "lint": "biome check", "format": "biome format --write" }, "dependencies": { "@orama/orama": "^3.1.18", "cnfast": "^0.0.8", "fumadocs-core": "16.10.7", "fumadocs-mdx": "15.0.13", "fumadocs-ui": "16.10.7",… Evidence: `website-fumadocs/package.json`
- **Package** (package_manifest): { "name": "kimetsu-remote", "version": "0.0.0", "description": "Kimetsu Remote beta — server-hosted Kimetsu brain over HTTP MCP. Installs the prebuilt native server binary for your platform. Separate from the kimetsu-ai CLI.", "keywords": "kimetsu", "mcp", "server", "brain", "remote" , "homepage": "https://github.com/RodCor/kimetsu readme", "bugs": { "url": "https://github.com/RodCor/kimetsu/issues" }, "repository": { "type": "git", "url": "git+https://github.com/RodCor/kimetsu.git", "directory": "npm/kimetsu-remote" }, "license": "MIT OR Apache-2.0", "type": "commonjs", "bin": { "kimetsu-remote": "bin/cli.js" }, "files": "bin/cli.js", "README.md" , "engines": { "node": " =16" }, "optionalD… Evidence: `npm/kimetsu-remote/package.json`
- **Package** (package_manifest): { "name": "kimetsu-ai", "version": "0.0.0", "description": "Kimetsu — a persistent memory brain sidecar for Claude Code and Codex. Installs the prebuilt native binary for your platform.", "keywords": "kimetsu", "mcp", "claude", "codex", "memory", "rag", "cli" , "homepage": "https://github.com/RodCor/kimetsu readme", "bugs": { "url": "https://github.com/RodCor/kimetsu/issues" }, "repository": { "type": "git", "url": "git+https://github.com/RodCor/kimetsu.git", "directory": "npm/kimetsu" }, "license": "MIT OR Apache-2.0", "type": "commonjs", "bin": { "kimetsu": "bin/cli.js", "kimetsu-ai": "bin/cli.js" }, "files": "bin/cli.js", "lib/embeddings.js", "README.md" , "engines": { "node": " =16" },… Evidence: `npm/kimetsu/package.json`
- **Contributor Covenant Code of Conduct** (documentation): Contributor Covenant Code of Conduct Evidence: `docs/CODE_OF_CONDUCT.md`
- **Fully-local Kimetsu: zero external network calls** (documentation): Fully-local Kimetsu: zero external network calls Evidence: `docs/LOCAL-MODELS.md`
- **Kimetsu Remote beta** (documentation): Run the brain on a server and connect over HTTP MCP , so a team or you across machines shares one brain per repository, with no local checkout. Evidence: `docs/REMOTE.md`
- **Kimetsu Algorithm** (documentation): How Kimetsu turns memory into measurable savings: every cited memory is credited with the tokens it saved, every injection is charged for the tokens it cost, and kimetsu brain roi reports the net. This page documents the exact accounting so the ledger can be audited rather than trusted. Evidence: `docs/ROI-METHODOLOGY.md`
- **Switching re-projects from the event log.** (documentation): Every knob in project.toml , the off-switches, and the environment overrides. Evidence: `docs/how-kimetsu-works/configuration.md`
- **The MCP surface** (documentation): The MCP tool surface, the host hooks that make the loop reliable, and proactive mid-work recall. Evidence: `docs/how-kimetsu-works/interfaces.md`
- **Citations + blame** (documentation): Citations, decay, dedup, conflict detection, and the analytics that prove the brain is helping. Evidence: `docs/how-kimetsu-works/learning-loop.md`
- **The bridge** (documentation): The bridge, brain sharing, doctor, and what Kimetsu is not. Evidence: `docs/how-kimetsu-works/operations.md`
- **Retrieval Models** (documentation): Which embedder and reranker Kimetsu ships, why, and how to swap or re-benchmark them. Evidence: `docs/how-kimetsu-works/retrieval-models.md`
- **Durable upgrades: schema migrations** (documentation): brain.db: the event-sourced SQLite file that holds everything Kimetsu remembers, and how it migrates safely. Evidence: `docs/how-kimetsu-works/the-brain.md`
- **Embeddings vs lean builds** (documentation): How the broker scores, selects, and budgets the memories injected into each run. Evidence: `docs/how-kimetsu-works/the-broker.md`
- **Results: 100K bucket** (documentation): How Kimetsu scores on BEAM, the ten-ability long-term-memory benchmark, at the 100K and 1M token buckets. Evidence: `docs/memory-benchmark/beam.md`
- **Brainbench** (documentation): BrainBench is Kimetsu's own reader-free capability benchmark: it drives the real binary across difficulty tiers and scores dedup, forgetting, importance, and calibration with no LLM in the loop. Evidence: `docs/memory-benchmark/brainbench.md`
- **How Kimetsu compares** (documentation): How Kimetsu compares to mem0, Cognee, Zep, and Letta on the shared public benchmarks, and what we do not yet claim. Evidence: `docs/memory-benchmark/comparison.md`
- **Results** (documentation): How Kimetsu scores on LongMemEval, the public long-term-memory benchmark, with the exact setup so the number can be reproduced and compared. Evidence: `docs/memory-benchmark/longmemeval.md`
- **Retrieval quality** (documentation): Kimetsu's retrieval and correctness numbers: recall, MRR, latency, stale-hit suppression, and contradiction resolution, all reproducible from the shipped CLI. Evidence: `docs/memory-benchmark/retrieval-and-correctness.md`
- **v0.4.7: distribution-ready metadata. Each member crate picks up** (source_file): workspace members = "crates/kimetsu-agent", "crates/kimetsu-brain", "crates/kimetsu-chat", "crates/kimetsu-cli", "crates/kimetsu-core", "crates/kimetsu-e2e", "crates/kimetsu-remote", resolver = "3" Evidence: `Cargo.toml`
- **v0.4.8: kimetsu-agent pulls kimetsu-brain for retrieval inside** (source_file): package name = "kimetsu-agent" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "Transport-neutral agent runtime for kimetsu: tools, prompts, verify-loop, providers claude code, anthropic, openai ." keywords = "kimetsu", "agent", "llm", "anthropic", "openai" categories = "development-tools" Evidence: `crates/kimetsu-agent/Cargo.toml`
- **Lib** (source_file): pub mod agent loop; pub mod anthropic; pub mod bedrock; pub mod bench; pub mod claude code; pub mod harness; pub mod model; pub mod openai; pub mod pipeline; pub mod recall ledger; pub mod swe bench; pub mod tools; Evidence: `crates/kimetsu-agent/src/lib.rs`
- **v0.4.3: opt into the local fastembed-rs embedder so kimetsu can do** (source_file): package name = "kimetsu-brain" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "Project + user-scope memory, hybrid retrieval lexical + cosine , ambient context, secret redaction at ingest for kimetsu." keywords = "kimetsu", "memory", "rag", "retrieval", "embeddings" categories = "database", "development-tools" Evidence: `crates/kimetsu-brain/Cargo.toml`
- **Ann** (source_file): use std::collections::HashMap; ⋮---- use rusqlite::Connection; ⋮---- use kimetsu core::KimetsuResult; ⋮---- struct Manifest { ⋮---- fn ann scalar kind - ScalarKind { match std::env::var "KIMETSU ANN QUANTIZATION" .ok .as deref { ⋮---- eprintln! "kimetsu-brain: unknown KIMETSU ANN QUANTIZATION '{other}', using f16" ; ⋮---- fn scalar kind id k: ScalarKind - &'static str { ⋮---- fn index options dim: usize - IndexOptions { ⋮---- quantization: ann scalar kind , ⋮---- /// Threads for parallel index construction. usearch add is thread-safe /// Index: Send+Sync, C++ locks internally , so fanning inserts across cores ⋮---- /// Index: Send+Sync, C++ locks internally , so fanning inserts across cores… Evidence: `crates/kimetsu-brain/src/ann.rs`
- **Conflict** (source_file): use kimetsu core::KimetsuResult; use kimetsu core::ids::new id; ⋮---- use time::OffsetDateTime; use time::format description::well known::Rfc3339; ⋮---- pub fn conflict detection enabled config value: bool - bool { ⋮---- let v = raw.trim .to ascii lowercase ; if v.is empty { ⋮---- !matches! v.as str , "0" "false" "off" "no" ⋮---- pub fn resolve conflicts enabled config value: bool - bool { ⋮---- pub enum ResolutionOutcome { ⋮---- pub fn resolution score confidence: f32, created at rfc3339: &str - f32 { ⋮---- let secs = now - ts .whole seconds .max 0 ; ⋮---- let recency weight = -std::f64::consts::LN 2 / HALF LIFE DAYS age days .exp as f32; confidence.clamp 0.0, 1.0 recency weight .clamp 0.0… Evidence: `crates/kimetsu-brain/src/conflict.rs`
- **cfg feature = "embeddings"** (source_file): use std::cmp::Ordering; use std::collections::HashMap; ⋮---- use kimetsu core::memory::MemoryScope; ⋮---- pub enum TaskKind { ⋮---- pub fn classify task task: &str - TaskKind { let lower = task.to ascii lowercase ; ⋮---- if DEBUG KW.iter .any kw lower.contains kw { ⋮---- if INVESTIGATE KW.iter .any kw lower.contains kw { ⋮---- if REFACTOR KW.iter .any kw lower.contains kw { ⋮---- if DOCS KW.iter .any kw lower.contains kw { ⋮---- fn weights for task kind base: StageWeights, kind: TaskKind - StageWeights { ⋮---- TaskKind::Debug = renorm StageWeights { ⋮---- TaskKind::Refactor = renorm StageWeights { ⋮---- TaskKind::Investigation = renorm StageWeights { ⋮---- TaskKind::Docs = renorm StageWeigh… Evidence: `crates/kimetsu-brain/src/context.rs`
- **derive Debug, Default, Clone, Copy** (source_file): use kimetsu core::KimetsuResult; ⋮---- pub trait Embedder: Send + Sync { ⋮---- fn is noop &self - bool { ⋮---- fn embed batch &self, texts: & &str - Result , EmbedderError { texts.iter .map t self.embed t .collect ⋮---- impl Embedder for Box { fn embed &self, text: &str - Result , EmbedderError { self .embed text ⋮---- fn model id &self - &str { self .model id ⋮---- fn dim &self - usize { self .dim ⋮---- self .is noop ⋮---- self .embed batch texts ⋮---- pub enum EmbedderError { ⋮---- fn fmt &self, f: &mut std::fmt::Formatter - std::fmt::Result { ⋮---- Self::NotImplemented = write! f, "embedder not implemented" , Self::LoadFailed msg = write! f, "embedder load failed: {msg}" , Self::EmbedFai… Evidence: `crates/kimetsu-brain/src/embeddings.rs`
- **Ingest** (source_file): use std::collections::HashSet; use std::fs; use std::io::Read; ⋮---- use kimetsu core::KimetsuResult; use kimetsu core::config::ProjectConfig; use kimetsu core::paths::ProjectPaths; ⋮---- use time::OffsetDateTime; ⋮---- pub struct RepoIngestSummary { ⋮---- struct IndexedFile { ⋮---- struct ManifestRecord { ⋮---- pub fn ingest repo ⋮---- let repo root = paths.repo root.canonicalize ?; let skip dirs = skip dirs config ; let max file bytes, max total files = effective ingest limits config ; ⋮---- .hidden false .git ignore true .git global true .git exclude true .filter entry move entry should descend entry, &skip dirs ; ⋮---- for result in builder.build { ⋮---- let path = entry.path ; ⋮---- le… Evidence: `crates/kimetsu-brain/src/ingest.rs`
- **Lib** (source_file): pub mod ambient; pub mod analytics; ⋮---- pub mod ann; ⋮---- pub crate mod backend; ⋮---- pub mod backend bench; pub mod benchmark; pub mod blame; pub mod conflict; pub mod conflicts; pub mod consolidate; pub mod context; ⋮---- pub mod digest; pub mod dropped capsule; pub mod embeddings; ⋮---- pub mod episode; pub mod eval; pub mod feedback; ⋮---- pub mod graph; pub mod graph build; pub mod ingest; ⋮---- pub mod lifecycle; pub mod lock; pub mod maintenance; pub mod migrate; pub mod packs; pub mod project; pub mod projector; pub mod redact; pub mod reindex; pub mod reinforce; pub mod roi; pub mod schema; pub crate mod scoring; pub mod skill synthesis; ⋮---- pub mod sync; pub mod trace; pub m… Evidence: `crates/kimetsu-brain/src/lib.rs`
- **Lifecycle** (source_file): use std::path::Path; ⋮---- use kimetsu core::KimetsuResult; ⋮---- use time::OffsetDateTime; use time::format description::well known::Rfc3339; ⋮---- pub enum InvalidationReason { ⋮---- impl InvalidationReason { ⋮---- pub fn as str &self - &'static str { ⋮---- /// Parse a free-text invalidated reason column value into the best /// matching variant. Unknown / pre-taxonomy strings → Manual . ⋮---- /// matching variant. Unknown / pre-taxonomy strings → Manual . pub fn from db s: &str - Self { ⋮---- pub fn from db s: &str - Self { let lower = s.to ascii lowercase ; match lower.as str { ⋮---- fn fmt &self, f: &mut std::fmt::Formatter - std::fmt::Result { f.write str self.as str ⋮---- pub struct F… Evidence: `crates/kimetsu-brain/src/lifecycle.rs`
- **doc hidden** (source_file): use std::fs; use std::path::PathBuf; ⋮---- use kimetsu core::KimetsuResult; use kimetsu core::ids::RunId; ⋮---- use time::OffsetDateTime; use ulid::Ulid; ⋮---- use crate::conflict; use crate::embeddings; use crate::project::MemoryRow; use crate::redact; use crate::schema; ⋮---- pub fn open user brain - KimetsuResult { if !user brain enabled { return Ok None ; ⋮---- let Some dir = user kimetsu dir else { ⋮---- let db path = dir.join "brain.db" ; ⋮---- Ok Some conn ⋮---- pub fn open user brain readonly - KimetsuResult { ⋮---- let Some db path = user brain db path else { ⋮---- if !db path.exists { ⋮---- .is some = ⋮---- Err e = return Err e , ⋮---- pub fn open user brain for config ⋮---- if !u… Evidence: `crates/kimetsu-brain/src/user_brain.rs`
- **v0.4.8: passthrough so kimetsu-cli --features embeddings can** (source_file): package name = "kimetsu-chat" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "Interactive REPL chat client + MCP sidecar + cross-harness bridge for kimetsu. Installs into Claude Code and Codex as a brain-managed memory layer." keywords = "kimetsu", "chat", "mcp", "claude-code", "codex" categories = "development-tools", "command-line-utilities" Evidence: `crates/kimetsu-chat/Cargo.toml`
- **Ask** (source_file): use std::path::Path; ⋮---- use kimetsu brain::project; ⋮---- use kimetsu core::env file::resolve env value; ⋮---- pub struct AskAnswer { ⋮---- pub fn is command query query: &str - bool { let q = query.trim .to ascii lowercase ; q.starts with "how do i " q.starts with "how to " q.starts with "what command " q.starts with "what's the command" q.starts with "whats the command" q.contains "run the command" q.contains "run command" ⋮---- pub fn reorder for command fastpath ⋮---- if !is command query query { ⋮---- commands.push cap ; ⋮---- others.push cap ; ⋮---- commands.extend others ; ⋮---- pub fn compose answer workspace: &Path, question: &str - AskAnswer { ⋮---- stage: "ask".to string , que… Evidence: `crates/kimetsu-chat/src/ask.rs`
- **Bridge** (source_file): use std::collections::HashMap; use std::fs; ⋮---- pub enum BridgeTarget { ⋮---- impl BridgeTarget { pub fn parse value: &str - Result { match value.trim .to ascii lowercase .as str { "claude" "claude-code" "cc" = Ok Self::ClaudeCode , "codex" = Ok Self::Codex , "kimetsu" = Ok Self::Kimetsu , "cursor" = Ok Self::Cursor , ⋮---- "openclaw" "claw" = Ok Self::OpenClaw , ⋮---- Err "this build was compiled without the OpenClaw integration; \ ⋮---- .to string ⋮---- "pi" = Ok Self::Pi , ⋮---- "pi" = Err "this build was compiled without the Pi integration; \ ⋮---- .to string , other = Err format! "unknown bridge target {other} " , ⋮---- pub const fn as str self - &'static str { ⋮---- pub enum PluginM… Evidence: `crates/kimetsu-chat/src/bridge.rs`
- **Lib** (source_file): pub mod ask; pub mod bridge; pub mod commands; pub mod cost; pub mod mcp server; pub mod repl; pub mod skills; pub mod ui; ⋮---- pub use commands::SlashCommand; pub use cost::CostMeter; Evidence: `crates/kimetsu-chat/src/lib.rs`
- **Mcp Server** (source_file): use std::str::FromStr; ⋮---- pub struct McpServeConfig { ⋮---- impl McpServeConfig { pub fn new workspace: PathBuf - Self { ⋮---- pub fn serve mcp ⋮---- .canonicalize .unwrap or else config.workspace.clone ; ⋮---- kimetsu brain::embeddings::apply embedder selection Some &project config.embedder.model ; ⋮---- for line in reader.lines { let line = line.map err err format! "read MCP stdin: {err}" ?; let line = line.trim start matches '\u{feff}' ; if line.trim .is empty { ⋮---- serde json::from str line .map err err format! "parse MCP request: {err}" ?; let Some id = request.get "id" .cloned else { ⋮---- let method = request.get "method" .and then Value::as str .unwrap or "" ; let params = requ… Evidence: `crates/kimetsu-chat/src/mcp_server.rs`
- **derive Debug, Clone, Serialize, Deserialize, PartialEq, Eq** (source_file): use std::collections::HashMap; ⋮---- use std::sync::mpsc; ⋮---- use crossterm::queue; ⋮---- use kimetsu agent::claude code::ClaudeCodeProvider; ⋮---- use kimetsu core::config::ProjectConfig; use kimetsu core::env file::resolve env value; use kimetsu core::ids::RunId; use kimetsu core::paths::user cache dir for; ⋮---- use crate::cost::CostMeter; ⋮---- pub struct ChatConfig { ⋮---- impl ChatConfig { pub fn new workspace root: impl Into - Self { ⋮---- workspace root: workspace root.into , ⋮---- model: "claude-opus-4-7".to string , ⋮---- pub type ChatResult = Result ; ⋮---- pub enum ChatError { ⋮---- fn fmt &self, f: &mut std::fmt::Formatter - std::fmt::Result { ⋮---- Self::Io e = write! f, "I/… Evidence: `crates/kimetsu-chat/src/repl.rs`
- **Skills** (source_file): use std::collections::HashSet; use std::fs; ⋮---- use serde::Serialize; ⋮---- pub struct SkillConfig { ⋮---- impl Default for SkillConfig { fn default - Self { ⋮---- pub enum SkillSource { ⋮---- impl SkillSource { pub const fn as str &self - &'static str { ⋮---- pub enum SkillRootKind { ⋮---- impl SkillRootKind { ⋮---- pub struct SkillRoot { ⋮---- pub struct SkillManifest { ⋮---- impl SkillManifest { pub fn resource summary &self - String { summarize resources &self.resources ⋮---- pub enum SkillResourceKind { ⋮---- impl SkillResourceKind { ⋮---- pub struct SkillResource { ⋮---- pub struct LoadedSkill { ⋮---- pub struct SkillRegistry { ⋮---- impl SkillRegistry { pub fn discover workspace: &… Evidence: `crates/kimetsu-chat/src/skills.rs`
- **v0.4.8: re-export the brain crate's embeddings feature so** (source_file): package name = "kimetsu-cli" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "Top-level kimetsu binary: chat client, MCP sidecar, bridge for Claude Code / Codex, brain admin tools, doctor." keywords = "kimetsu", "cli", "ai", "chat", "agent" categories = "command-line-utilities", "development-tools" Evidence: `crates/kimetsu-cli/Cargo.toml`
- **Ask** (source_file): mod tests { ⋮---- fn is command query delegated correctly { assert! kimetsu chat::ask::is command query ⋮---- assert! kimetsu chat::ask::is command query "how to install deps" ; assert! !kimetsu chat::ask::is command query ⋮---- fn compose answer graceful for missing workspace { let tmp = std::env::temp dir .join format! ⋮---- let ans = compose answer &tmp, "how do I run tests?" ; assert! Evidence: `crates/kimetsu-cli/src/ask.rs`
- **derive Debug** (source_file): use std::env; ⋮---- use std::str::FromStr; ⋮---- use kimetsu brain::project; use kimetsu core::KimetsuResult; ⋮---- pub crate fn brain command: BrainCommand - KimetsuResult { ⋮---- if !matches! command, BrainCommand::Model { .. } { apply embedder from cwd ; ⋮---- println! "repo root: {}", summary.repo root.display ; println! "indexed files: {}", summary.indexed files ; println! "skipped files: {}", summary.skipped files ; println! "manifests: {}", summary.manifests ; Ok ⋮---- if capsules.is empty { println! "no file matches" ; return Ok ; ⋮---- println! ⋮---- .ok .and then paths project::load config &paths .ok ; ⋮---- .as ref .map cfg cfg.broker.ambient .unwrap or true ; ⋮---- augmented, So… Evidence: `crates/kimetsu-cli/src/commands/brain.rs`
- **Chat** (source_file): use std::env; ⋮---- use std::str::FromStr; ⋮---- use kimetsu brain::project; use kimetsu core::KimetsuResult; ⋮---- pub crate fn chat args: ChatArgs - KimetsuResult { ⋮---- && !m.is empty ⋮---- let stdin = stdin ; let stdout = stdout ; config.raw terminal input = stdin.is terminal && stdout.is terminal ; ⋮---- config.ui = if !args.plain && stdout.is terminal && rich ui enabled from env { ⋮---- .with logo !args.no logo ; ⋮---- let workspace = config.workspace root.canonicalize ?; ⋮---- .map err err format! "kimetsu chat --list-skill-sources: {err}" ?; if registry.roots .is empty { println! "no skill sources configured" ; ⋮---- for root in registry.roots { ⋮---- let login = match root.kind.as… Evidence: `crates/kimetsu-cli/src/commands/chat.rs`
- **Lifecycle** (source_file): use std::env; ⋮---- use std::str::FromStr; ⋮---- use kimetsu brain::project; use kimetsu core::KimetsuResult; ⋮---- pub crate fn update cmd args: UpdateArgs - KimetsuResult { ⋮---- pub crate fn uninstall cmd args: UninstallArgs - KimetsuResult { ⋮---- pub crate fn checkpoint cmd args: CheckpointArgs - KimetsuResult { ⋮---- .unwrap or else env::current dir .unwrap or default ; let note = args.note.as deref .unwrap or "" ; ⋮---- // Use capture episode now with an empty transcript manual save does not // require a transcript — the note itself is sufficient context . ⋮---- println! " Kimetsu Work checkpoint saved." ; if !note.is empty { println! " Note: {note}" ; ⋮---- // Could not write — like… Evidence: `crates/kimetsu-cli/src/commands/lifecycle.rs`
- **Memory** (source_file): use std::env; ⋮---- use std::str::FromStr; ⋮---- use kimetsu brain::project; use kimetsu core::KimetsuResult; ⋮---- pub crate fn stats - KimetsuResult { ⋮---- println! "memories: {}", memories.len ; println! "runs: {}", runs.len ; Ok ⋮---- pub crate fn memory command: MemoryCommand - KimetsuResult { ⋮---- if let Some base url = args.remote.remote.as deref { ⋮---- let repo = args.remote.repo.as deref .ok or else { "kimetsu brain memory add --remote requires --repo ".to string ⋮---- let token = remote client::resolve token args.remote.token.as deref ?; ⋮---- println! "{}", remote client::render result &result ; ⋮---- println! "memory id: {id}" ; ⋮---- MemoryCommand::AddBatch args = memory add… Evidence: `crates/kimetsu-cli/src/commands/memory.rs`
- **Mod** (source_file): pub crate mod bench; pub crate mod brain; pub crate mod chat; pub crate mod config; pub crate mod hooks; pub crate mod hosts; pub crate mod integrations; pub crate mod lifecycle; pub crate mod memory; pub crate mod runs; Evidence: `crates/kimetsu-cli/src/commands/mod.rs`
- **Mod** (source_file): pub mod proto; ⋮---- pub mod ipc; ⋮---- pub mod server; ⋮---- pub mod client; Evidence: `crates/kimetsu-cli/src/embed_daemon/mod.rs`
- **arg long, default value t = 12** (source_file): use std::env; ⋮---- use std::path::PathBuf; ⋮---- mod ask; mod commands; mod distiller; mod doctor; mod embed daemon; mod harvest setup; mod proactive state; mod process; mod remote client; mod skill synth; mod update; ⋮---- use kimetsu core::KimetsuResult; ⋮---- use tracing subscriber::EnvFilter; ⋮---- const VERSION: &str = env! "KIMETSU VERSION DISPLAY" ; ⋮---- struct Cli { ⋮---- enum Command { ⋮---- struct DoctorArgs { ⋮---- struct UpdateArgs { ⋮---- struct UninstallArgs { ⋮---- struct PsArgs { ⋮---- struct StopArgs { ⋮---- struct RestartArgs { ⋮---- struct ChatArgs { ⋮---- enum BridgeCommand { ⋮---- struct BridgeWorkspaceArgs { ⋮---- struct BridgeImportArgs { ⋮---- struct BridgeExportAr… Evidence: `crates/kimetsu-cli/src/main.rs`
- **Cargo** (source_file): package name = "kimetsu-core" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "Shared core types config, events, ids, paths, memory kinds for the kimetsu agent runtime + brain." keywords = "kimetsu", "ai", "agent", "llm" categories = "development-tools" Evidence: `crates/kimetsu-core/Cargo.toml`
- **Lib** (source_file): pub mod clock; pub mod config; pub mod env file; pub mod event; pub mod ids; pub mod memory; pub mod paths; pub mod secret; ⋮---- pub type KimetsuResult = Result ; Evidence: `crates/kimetsu-core/src/lib.rs`
- **Memory** (source_file): use std::str::FromStr; ⋮---- pub enum MemoryScope { ⋮---- impl Display for MemoryScope { fn fmt &self, f: &mut Formatter - std::fmt::Result { ⋮---- f.write str value ⋮---- impl FromStr for MemoryScope { type Err = String; ⋮---- fn from str value: &str - Result { ⋮---- "global user" "global-user" "user" = Ok Self::GlobalUser , "project" = Ok Self::Project , "repo" "repository" = Ok Self::Repo , "run" = Ok Self::Run , = Err format! "unknown memory scope: {value}" , ⋮---- pub enum MemoryKind { ⋮---- impl Display for MemoryKind { ⋮---- impl FromStr for MemoryKind { ⋮---- "preference" = Ok Self::Preference , "convention" = Ok Self::Convention , "command" = Ok Self::Command , "failure pattern" "f… Evidence: `crates/kimetsu-core/src/memory.rs`
- **v0.5.3: this crate is a test harness, not a library users consume.** (source_file): package name = "kimetsu-e2e" version.workspace = true edition.workspace = true license.workspace = true authors.workspace = true repository.workspace = true homepage.workspace = true documentation.workspace = true readme.workspace = true rust-version.workspace = true description = "v0.5.3: in-process end-to-end test suite for the kimetsu agent loop + brain pipeline. Not published — integration test harness only." keywords = "kimetsu", "testing", "internal" categories = "development-tools::testing" v0.5.3: this crate is a test harness, not a library users consume. Stays out of crates.io for the same reason kimetsu-harbor-rs does. publish = false Evidence: `crates/kimetsu-e2e/Cargo.toml`
- The remaining 19 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`, `npm/README.md`, `website-fumadocs/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`, `npm/README.md`, `website-fumadocs/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, Cargo.toml, crates/kimetsu-core/src/lib.rs, crates/kimetsu-brain/src/lib.rs, crates/kimetsu-cli/src/main.rs
- **Memory Pipeline, Retrieval & Scoring**: importance `high`
  - source_paths: crates/kimetsu-brain/src/ingest.rs, crates/kimetsu-brain/src/embeddings.rs, crates/kimetsu-brain/src/ann.rs, crates/kimetsu-brain/src/scoring.rs, crates/kimetsu-brain/src/context.rs
- **CLI Commands, Operations & Maintenance**: importance `high`
  - source_paths: crates/kimetsu-cli/src/main.rs, crates/kimetsu-cli/src/commands/mod.rs, crates/kimetsu-cli/src/commands/brain.rs, crates/kimetsu-cli/src/commands/chat.rs, crates/kimetsu-cli/src/commands/lifecycle.rs
- **Host Integration, Plugins, MCP & Remote Server**: importance `high`
  - source_paths: crates/kimetsu-chat/src/lib.rs, crates/kimetsu-chat/src/mcp_server.rs, crates/kimetsu-chat/src/repl.rs, crates/kimetsu-chat/src/ask.rs, crates/kimetsu-chat/src/skills.rs

## Repo Inspection Evidence

- repo_clone_verified: true
- repo_inspection_verified: true
- repo_commit: `42c8179bff538b81d620a8b48a61b18a5fc303ca`
- inspected_files: `README.md`, `docs/CODE_OF_CONDUCT.md`, `docs/CONTRIBUTING.md`, `docs/INSTALL.md`, `docs/LOCAL-MODELS.md`, `docs/REMOTE.md`, `docs/ROI-METHODOLOGY.md`, `docs/how-kimetsu-works/configuration.md`, `docs/how-kimetsu-works/index.md`, `docs/how-kimetsu-works/interfaces.md`, `docs/how-kimetsu-works/learning-loop.md`, `docs/how-kimetsu-works/operations.md`, `docs/how-kimetsu-works/retrieval-models.md`, `docs/how-kimetsu-works/the-brain.md`, `docs/how-kimetsu-works/the-broker.md`, `docs/memory-benchmark/beam.md`, `docs/memory-benchmark/brainbench.md`, `docs/memory-benchmark/comparison.md`, `docs/memory-benchmark/index.md`, `docs/memory-benchmark/longmemeval.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/RodCor/kimetsu
- 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/RodCor/kimetsu
- 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/RodCor/kimetsu
- 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/RodCor/kimetsu
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.

### Constraint 5: Maintenance risk requires verification

- Trigger: release_recency=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/RodCor/kimetsu
- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.