{
  "markdown": "# Project Memory\n\nProject Memory keeps a project's decisions, evidence, outcomes and reviewed lessons in a local SQLite database. An AI assistant retrieves the relevant records through three MCP tools; people inspect the same history in a self-contained HTML viewer.\n\nUse it when a project repeatedly revisits research, loses the reasons behind decisions, or carries outdated requirements into new work. It preserves the original evidence and the conditions under which a decision or lesson applies.\n\n**Public beta.** The runtime uses Python 3.11+ and its standard library. There is no model service, vector database, telemetry or background maintenance process. The assistant still interprets evidence and needs explicit agreement before accepting a lesson or changing project requirements. [Evidence and limits](docs/evidence.md) describe what has actually been measured.\n\n<!-- mcp-name: io.github.Dankaro-projects/project-memory -->\n\n## Install and connect\n\nInstall [uv](https://docs.astral.sh/uv/getting-started/installation/), then run this **inside the project you want to remember**:\n\n```sh\nuvx project-memory-mcp@0.5.0b1 setup --client codex --trust\n```\n\nThis creates `.memory/project.sqlite`, adds a project-local MCP connection and nine command hooks, and asks the installed Codex host for the exact hook hashes to enable. Existing settings and records are preserved. Open a new Codex task afterwards. `--trust` explicitly enables these project hooks; omit it to review and enable them in Codex yourself.\n\nFor a permanent CLI installation:\n\n```sh\nuv tool install project-memory-mcp==0.5.0b1\nproject-memory doctor\nproject-memory view\n```\n\nFor another local MCP client, run `project-memory setup --client mcp`, then configure the client to run `project-memory serve --project /absolute/path/to/project`. Generic MCP supports explicit records and retrieval; Codex's automatic receipts are a separately verified integration. [Setup and lifecycle](docs/setup.md) includes imports, upgrades, backup, uninstall and client configuration.\n\nThe same versioned wheel is available from [GitHub Releases](https://github.com/Dankaro-projects/project-memory/releases). The MCPB asset supports directory selection in compatible desktop clients.\n\n![The HTML viewer shows synthetic decisions, evidence, corrections and review status.](https://raw.githubusercontent.com/Dankaro-projects/project-memory/main/docs/images/viewer.png)\n\n## Use it in ordinary work\n\nAsk your assistant:\n\n> Capture VISION.md and our decision log. Show which statements are evidence, proposals and agreed requirements. Preserve the originals. Before choosing an approach, retrieve relevant decisions and check whether their evidence is still current.\n\nThen work normally. The assistant supplies record IDs and versions. You review the meaning, rather than maintain a second set of forms.\n\n- A decision records its evidence, initial choice, alternatives, uncertainty, expected consequences and conditions for reconsideration.\n- Actions and actual outcomes attach to that decision. Revisions retain the earlier choice and its result.\n- Successful practices, anti-patterns and recoveries can become proposed lessons. A separate review accepts, rejects or retires them, with their scope and exceptions intact.\n- Code reviews, writing corrections and research remain separate subjects. A dependency across subjects must name the evidence and explain why it matters.\n- Selected Markdown files are captured verbatim. Changed, missing and superseded evidence is flagged. Importing a vision does not approve its proposals.\n- Approved project requirements can evolve through append-only revisions. Earlier decisions retain the version they used and become reviewable when the agreed basis changes.\n\nRun `project-memory view` for decisions, documents, corrections, patterns, drift, captures and unresolved work. It creates a fresh, offline HTML snapshot with evidence navigation. Source bodies are excluded unless you add `--include-bodies`.\n\n## What is automatic\n\nCodex hooks mechanically record session and tool events, sizes, hashes and available execution metadata. They do not turn a failed command into a lesson or assume that an interrupted command rolled back. The assistant records interpretation separately and checks side effects before retrying uncertain work.\n\nRetrieval returns bounded, complete records and preserves exceptions. Search indexes and explicit source slices support expansion when needed. The default MCP reply limit is 6,000 characters, with an explicit maximum of 20,000; these are **characters in the tool result, not complete model-input tokens**. Keeping every model input below 10K tokens remains a target, subordinate to quality and feature preservation.\n\n## Develop and verify\n\n```sh\npython -m unittest discover -s tests -q\npython -m examples.document_case --output results/documents\npython -m examples.host_example --output results/host-example\nnode tests/viewer_logic.cjs\nuv build\npython scripts/check_artifacts.py dist\npython scripts/installed_smoke.py dist\n```\n\nThe public artifacts contain code, documentation and synthetic examples. They exclude project databases, host transcripts, private evaluation archives and local configuration. [Contributing](CONTRIBUTING.md), [security](SECURITY.md), [record fields](docs/record-fields.md), [release process](docs/releasing.md).\n",
  "bytes": 5369,
  "sha": "5ec3066741d84adb852b67df22bcf3d9ed78a92c88040b7c9f8e26752bf4dbdd",
  "repo_slug": "dankaro-projects/project-memory",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_dankaro_projects_project_memor_ce01e2a7/readme"
}