by riponcm
Local-first memory layer for AI coding agents. Captures issues, attempts, decisions, and cross-project library gotchas — your AI starts experienced, not amnesiac. Native MCP server verified across Claude Desktop, Cursor, Antigravity, and Codex. 100% local · no cloud · no telemetry · MIT.
# Add to your Claude Code skills
git clone https://github.com/riponcm/projectmemLast scanned: 6/27/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-27T06:53:17.787Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}projectmem is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by riponcm. Local-first memory layer for AI coding agents. Captures issues, attempts, decisions, and cross-project library gotchas — your AI starts experienced, not amnesiac. Native MCP server verified across Claude Desktop, Cursor, Antigravity, and Codex. 100% local · no cloud · no telemetry · MIT. It has 100 GitHub stars.
Yes. projectmem passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/riponcm/projectmem" and add it to your Claude Code skills directory (see the Installation section above).
projectmem is primarily written in Python. It is open-source under riponcm on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh projectmem against similar tools.
No comments yet. Be the first to share your thoughts!
| Doc | What's in it |
|---|---|
| TUTORIAL.md | 15-minute step-by-step walkthrough — set up projectmem on your own project, watch the lifecycle, see the pre-commit warning fire. |
| CHANGELOG.md | Release history. Latest: v0.1.4 — the accountable-judgment release: stale-memory detection, decision supersede, precheck snooze, pjm brief, failed-approach surfacing, CLAUDE.md export, dashboard Overview. |
| Research paper (arXiv:2606.12329) | PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents — the peer-readable version: design, Memory-as-Governance framing, capability comparison, and the 207-event dogfooding study. |
| LICENSE | MIT |
Every new AI session starts from zero. Claude, Cursor, Aider — they all forget yesterday's decisions, repeat failed debugging attempts, and burn millions of tokens reconstructing context from raw source files.
The model isn't the problem. The architecture is. Stateless models need a memory cortex.
projectmem is the local-first memory + judgment layer that sits above your AI tools. It captures every failed attempt, decision, and gotcha — then injects that experience back into future AI sessions. Git tracks what changed. projectmem tracks why it changed, what was tried, and what failed.
pip install projectmem
cd your-project
pjm init
That's it. pjm init installs three git hooks (pre-commit warnings, post-commit classification, post-merge tracking), auto-starts a real-time file watcher, inherits cross-project memory if available, and creates .projectmem/. Capture is active from minute one.
The canonical command is
projectmem. Apjmalias is installed for speed.
pjm precheck warns you before you commit if you're about to repeat a failed approach, modify a high-churn file, or touch an unresolved issue. No other AI tool does this — it requires the memory layer underneath. The warning now lists the dead ends themselves ("What already failed here: ✗ tried CSS contain:layout"), and pjm precheck --snooze 2h silences it politely — the snooze is itself logged, so even the silence is audited.pjm decision "new way" --supersedes <id>: the old event stays in the log, tagged, forever.pjm brief answers "where was I?" in one screen: active warnings, possibly-stale memories, open issues, recent decisions, stack gotchas, and your prevention score with a week-over-week delta.pjm export --claude-md compiles live decisions, gotchas, and a "Do NOT retry — these already failed" list into a marked block in CLAUDE.md (or .cursorrules). Copilot, plain Claude, any agent that reads the file inherits your project's judgment.pjm wrap claude (or cursor/aider) injects a token-budgeted memory block into your AI before the session opens. Your AI starts experienced, not blank.pjm score outputs a letter grade (A+ → F) backed by concrete numbers — debugging hours saved, tokens prevented, dollars protected. CI-friendly JSON output and shields.io badge for your README.~/.projectmem/global/ and auto-inherit into every new project that matches your stack.pjm init.pjm visualize opens a four-tab D3.js dashboard: Story Map (failure heatmap), ROI Dashboard, Project Map (tree or graph view), Timeline.| Capability | projectmem | claude-mem | agentmemory | mem0 | Letta (MemGPT) |
|---|---|---|---|---|---|
| Core focus | Memory + Judgment | Session capture | Memory engine | Chat memory | Agent framework |
| Pre-commit failure warnings | ✅ unique | ❌ | ❌ | ❌ | ❌ |
| Stale memory: flag, never delete | ✅ new in 0.1.4 | ❌ | ❌ silent decay | ❌ | ❌ |
| Supersede without losing history | ✅ new in 0.1.4 | ❌ | ❌ | ❌ | ❌ |
| Captures development history | ✅ typed events | 🟡 | 🟡 | 🟡 | 🟡 |
| Records architectural decisions | ✅ | ❌ | 🟡 | ❌ | ❌ |
| Memory for agents without MCP | ✅ CLAUDE.md export | ❌ | ❌ | ❌ | 🟡 |
| Cross-project memory | ✅ library-scoped | 🟡 | 🟡 | 🟡 | 🟡 |
| Provable ROI score | ✅ A+ → F + $ | ❌ | ❌ | ❌ | ❌ |
| Plain-text, greppable store | ✅ events.jsonl | ❌ | ❌ | ❌ | 🟡 |
| No server / DB to run | ✅ stdio + files | ❌ | ❌ | ❌ | ❌ server + DB |
| No telemetry, no accounts | ✅ | ❌ default-on | ✅ | ❌ | 🟡 |
| Native MCP server | ✅ 14 focused tools | ✅ | 🟡 53 tools | 🟡 | 🟡 |
| Price | ✅ Free · MIT | Free + paid tier | Free | Freemium | Free + cloud |
✅ yes · 🟡 partial · ❌ no — snapshot June 2026; design capabilities, not benchmark results. claude-mem runs a background worker (port 37777) and enables telemetry by default (v13.5+); agentmemory down-ranks and prunes old memories via decay, mem0 rewrites facts on update, Letta's memory blocks self-edit in place — projectmem never deletes: it flags staleness and lets you decide. Letta requires a running server (Postgres or cloud).
The architecture is built around one rule: AI reads small, distilled files. Tools generate them from the big raw log.
| Access mode | Tokens / session | How it works |
|---|---|---|
| No projectmem (baseline) | 5,000 – 20,000+ | AI re-reads source files every session |
| Universal Mode (markdown) | ~2,500 | AI reads 3 small distilled files once |
| MCP Mode (recommended) | ~800 – 1,500 | AI calls get_summary(), then get_issue(id) only when relevant |
pjm wrap (pre-injection) |
500 – 2,000 | Pre-generated, you set the budget |
AI never reads events.jsonl directly. That file is for tools (pjm score, pjm context, pjm wrap). Tools distill the raw log into compact AI-readable summaries.
Easiest — open the config from the UI:
Settings… → Developer tab → Local MCP servers → Edit Config.Settings → Developer → Edit Config) — open an issue if your platform differs and we'll update this.If you prefer the raw file path: ~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows.
Paste this block:
"mcpServers": {
"projectmem": {
"command": "/opt/ana