# projectmem

> projectmem is free, open-source coding agent memory — a local-first memory + judgment layer for AI coding agents (Claude Code, Claude Desktop, Cursor, Antigravity, Codex). It records development history as typed events in plain text, feeds it back to the AI via MCP, and warns at git commit before you repeat a failed fix. Published by Matily (nonprofit). Paper: arXiv:2606.12329. Install: pip install projectmem

## Docs
- [FAQ](https://projectmem.dev/faq/): direct answers on projectmem, AI agent memory, MCP, and comparisons
- [Guide](https://projectmem.dev/guide/): setup for Claude Desktop / Cursor / Antigravity / Codex
- [Demo](https://projectmem.dev/demo/): live dashboard on a sample project
- [Changelog](https://projectmem.dev/changelog/): every release (latest: v0.2.0)
- [Blog](https://projectmem.dev/blog/): releases and deep dives
- [GitHub](https://github.com/riponcm/projectmem): source, issues, contributions
- [PyPI](https://pypi.org/project/projectmem/): package

## Articles
- [The Complete projectmem Guide: Give Your AI Coding Agent a Real Memory](https://projectmem.dev/blog/projectmem-complete-guide-ai-coding-agent-memory/): Install projectmem, connect it to Claude, Cursor or Codex, verify it with pjm doctor, and read your project's memory back through the dashboards — a complete walkthrough with real captured terminal output at every step.
- [AI Memory for Coding Agents in 2026: projectmem, OpenMemory, Graphify and MemRL Compared](https://projectmem.dev/blog/ai-memory-for-coding-agents-compared/): Four open-source tools now give AI coding agents memory — and they remember completely different things. A structural map, a preference store, an RL-scored episode log, and a typed record of what failed. Here is what each actually stores, and which one fits which problem.
- [projectmem v0.2.0: The Workspace Release — a Cross-Project Global Dashboard, Code Structure & Relations, and plan.md](https://projectmem.dev/blog/projectmem-v020-workspace-release-global-dashboard-code-structure-plan/): projectmem v0.2.0 lifts memory from one project to your whole machine. pjm dashboard puts every repo you've init-ed in a single local view, pjm map --build reads your code into a real structure graph with failure heat laid on top, and a new plan.md keeps intent separate from the event log. 15 MCP tools, no schema changes, still 100% local.
- [projectmem v0.1.6: Watch Your Project's Memory — Showoff Scenes, a Built-In Recorder, Flow Maps and the Time Spine](https://projectmem.dev/blog/projectmem-v016-visualization-release-showoff-flow-time-spine/): projectmem v0.1.6 is the visualization release: a new Showoff tab plays your project's history as animated scenes (and records a shareable video, 100% locally), the Project Map gains a Flow layout that reads like a story, and the Timeline becomes a Time Spine — problems branching left, knowledge branching right.
- [projectmem v0.1.4: Stale-Memory Detection for AI Coding Agents — Flag, Never Delete](https://projectmem.dev/blog/projectmem-v014-stale-memory-detection-ai-coding-agents/): projectmem v0.1.4 is the accountable-judgment release: stale-memory detection that flags outdated decisions instead of deleting them, supersede without losing history, a polite pre-commit snooze, the pjm brief session briefing, and CLAUDE.md export so even agents without MCP inherit your project's judgment.
- [projectmem v0.1.3: Schema-Enriched MCP Tools, Secret Redaction, and the Conda/Venv Hook Fix](https://projectmem.dev/blog/projectmem-v013-schema-redaction-hook-fix/): projectmem v0.1.3 lands six focused improvements: every MCP tool now exposes rich parameter descriptions and schema-level constraints (record_attempt.outcome is enforced at the schema), API keys and tokens are scrubbed from event text before they touch disk, the pre-commit warning now actually fires under conda/pyenv/venv where it had been silently broken for most Python users, pjm init pre-populates PROJECT_MAP from your manifests, and it prints a copy-pasteable MCP client config block at the end. Six improvements, one release.
- [projectmem v0.1.1: The First Local-First Cross-Project Memory Layer for AI Coding Agents](https://projectmem.dev/blog/projectmem-v011-cross-project-memory-launch/): projectmem v0.1.1 ships the first open-source local-first cross-project memory layer for AI coding agents — verified end-to-end across Claude Desktop, Cursor, Antigravity, and Codex, and across JavaScript, Python, and Go. Library gotchas learned in one project surface automatically in every other. 100% local, MIT, install in two commands.
- [How to Give Claude Code Persistent Memory in 2026 (Step-by-Step Guide)](https://projectmem.dev/blog/how-to-give-claude-code-persistent-memory/): Claude Code forgets everything between sessions. This step-by-step tutorial shows you exactly how to give it persistent memory using projectmem and the Model Context Protocol — in under 60 seconds. Free, local, MIT-licensed.
- [How to Cut Your Claude and Cursor AI Token Costs by 50%+ Without Switching Models](https://projectmem.dev/blog/reduce-claude-cursor-ai-token-costs/): AI coding bills are eating engineering budgets in 2026. Most of the cost is waste — the same context rebuilt across sessions, the same bugs debugged twice, the same prompts repeated. Here are five proven techniques to cut your Claude and Cursor token costs in half, ranked by impact.
- [What Is MCP (Model Context Protocol)? A Developer's Guide to Anthropic's Open Standard](https://projectmem.dev/blog/what-is-mcp-model-context-protocol-developer-guide/): MCP is the open protocol that lets AI tools call local servers in 2026 — and it's quietly becoming as important as HTTP for AI development. Here's what MCP is, why it matters, how it works, and how to build your first MCP server in under 30 minutes.
- [Why Your AI Coding Assistant Keeps Suggesting Fixes That Already Failed](https://projectmem.dev/blog/stop-ai-repeating-same-bugs/): Claude Code, Cursor, and Aider all share the same blind spot: they don't remember the approaches you already tried that didn't work. Here's why stateless AI keeps walking into the same wall — and how a memory + judgment layer makes your AI experienced instead of just smarter.
- [Comparing the Top 5 AI Memory Tools for Developers in 2026: projectmem, claude-mem, Graphify, mem0, and Cursor](https://projectmem.dev/blog/best-ai-memory-tools-comparison-2026/): AI memory tools exploded in 2026. Five projects now compete to give Claude Code, Cursor, and Aider persistent project context. We built one of them — and we'll show you honestly which tool wins on which dimension, with no marketing fluff.
- [projectmem v0.0.6 Released: Adding Judgment to AI Memory](https://projectmem.dev/blog/projectmem-v006-intelligence-layer-release/): Today we shipped v0.0.6 — the biggest release since projectmem launched. Pre-commit failure warnings, real-time file watcher, prevention score, cross-project memory inheritance, smart context injection, and 14 native MCP tools. Save up to 50%+ of AI tokens with zero configuration.
- [Coding Agent Memory for Claude Code: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-claude-code/): How to give Claude Code persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for Cursor: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-cursor/): How to give Cursor persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for Codex: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-codex/): How to give Codex persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for GLM: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-glm/): How to give GLM persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for Grok Build: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-grok-build/): How to give Grok Build — xAI's terminal coding agent — persistent coding agent memory with projectmem: install, initialise, connect. Every issue, attempt, fix and decision remembered across sessions, 100% locally.
- [Coding Agent Memory for Qwen: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-qwen/): How to give Qwen persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for OpenCode: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-opencode/): How to give OpenCode persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for Hermes: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-hermes/): How to give Hermes persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for DeepSeek: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-deepseek/): How to give DeepSeek persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.
- [Coding Agent Memory for Kimi: Setup Guide (2026)](https://projectmem.dev/blog/coding-agent-memory-for-kimi/): How to give Kimi persistent coding agent memory with projectmem: install, initialise, connect — then every issue, attempt, fix and decision is remembered across sessions, 100% locally.

## Full content
- [llms-full.txt](https://projectmem.dev/llms-full.txt): the complete FAQ and every article as plain markdown