Projectmem

🎉 v0.3.5 is out — precheck recognises a file however its path is spelled, and the summary stays small even when entries are long. See what changed →

We don't make AI smarter. We make it experienced. Coding agent memory — the local-first memory + judgment layer for AI coding agents. One MCP server for every project. Stop re-reading your project every session. Stop repeating yesterday's bug.

Website • Guide • Demo • Changelog • Paper

https://github.com/user-attachments/assets/e055988e-7253-4ba9-92fc-95d3d4bcd763

pjm visualize — every case your project solved, what failed on the way, and what it saved. Generated locally from .projectmem/events.jsonl .

---

## 🚀 Start here — five minutes, once

*Five minutes if you follow along here. Want to be shown instead — every

command, the exact output it prints back, and the dashboards at the end?

Take [the complete setup guide](https://projectmem.dev/blog/projectmem-complete-guide-ai-coding-agent-memory).*

New to projectmem, or upgrading from 0.1.x / 0.2.x? Since 0.3.0 one MCP

server serves every project, so this is the last time you configure anything.

1. Install or update

`bash

pip install -U projectmem

`

2. Find the projects you already have

`bash

pjm doctor

`

It looks where code lives — ~/Developer, ~/code, ~/projects, your cloud

folders, and every drive on Windows — and lists projects with memory that

aren't registered yet. Anything it missed, add by hand:

`bash

pjm project register "/Users/you/Developer/repos/ossdrop"

`

3. Register them

`bash

pjm doctor --fix

`

4. Point your AI at all of them with one config

`json

"mcpServers": {

"projectmem": {

"command": "/absolute/path/to/python",

"args": ["-m", "projectmem.mcp_server"]

}

}

`

No --root, no cwd — that's what makes it serve everything. Per-client

instructions (Claude Desktop, Claude Code, Cursor, Antigravity, Codex) are in

MCP Integration; pjm init prints this block

with your own Python path filled in. Then fully restart the client — MCP

servers only load on a cold start.

5. Check your work

`bash

pjm doctor

`

Add --online if you also want it to tell you when a newer projectmem is out

— projectmem makes no network calls otherwise, and --auto turns that into a

once-a-day check if you prefer.

Run it again after editing the config. It flags any client still pinned to a

single repo — the most common reason a new project is invisible to your agent.

All green? You're done. From here on it is one command per repo:

`bash

pjm init

`

Your agent reads what the project already learned instead of rediscovering it,

and writes down what it finds. Fewer tokens, no repeated dead ends, memory that

outlives the session.

---

What is coding agent memory?

Coding agent memory is a persistent record of what happened while building a project — the issues hit, the approaches attempted, the fixes that worked and the decisions made — stored so an AI coding agent can read it at the start of a new session. Without it every session begins from zero.

projectmem is an open-source agent memory layer built for that job. It is local-first: memory lives in a plain .projectmem/ directory inside your repository, with no cloud, no account and no telemetry — the only network call it can make is an update check you turn on yourself. A native MCP server exposes 17 tools to Claude Code, Claude Desktop, Cursor, Antigravity and Codex, so your agent reads memory and logs its work on its own.

Unlike chat-history memory tools, projectmem stores typed events — issues, attempts, fixes, decisions, notes — which is what makes its signature feature possible: a pre-commit warning that fires *before* you repeat an approach that already failed in this project.

pip install projectmem

cd your-project && pjm init

---

🎬 Watch the demo

Full screen-recorded tutorial- watch on YouTube

📚 Docs

---

The Problem

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.

The Solution

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.

Install

First time here? → [The complete setup guide](https://projectmem.dev/blog/projectmem-complete-guide-ai-coding-agent-memory)

walks the whole path end to end: install, connecting Claude Desktop, Claude Code,

Cursor, Codex or Antigravity, checking it with pjm doctor, and reading your

memory back through the dashboards — with the real terminal output at every step.

Three commands to a project that remembers:

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. A pjm alias is installed for speed.

---

✨ New in 0.3.5 — warnings for every spelling, and a summary that stays small

Precheck recognises a file however its path is spelled. Events store project-relative paths, so asking about ./src/auth.py, an absolute path, a path through a symlinked folder or a Windows C:\ path matched nothing, and precheck called a file with known failures "Safe to modify". Every spelling now gets the same warnings, and checking is faster on large logs. get_issue("1") and get_issue("#1") find issue 0001. (#26)

Long entries no longer bloat the summary. 0.3.4 capped how many entries the summary shows, not how long each one is. Records are now clipped at 300 characters, and a fixed issue takes one line. On a real 238-event project the summary went from 8,974 tokens to 3,458. (#29, #30)

Upgrading? Run `pjm init` once in each project. The instructions now ask agents for shorter records, and pjm init refreshes AI_INSTRUCTIONS.md, keeping your previous copy as AI_INSTRUCTIONS.md.bak.

The #26 fixes were contributed by @vishalhabib99, and #29 was reported and fixed by @bigfree.

✨ New in 0.3.4 — memory that stays small, and warnings you can trust

The summary no longer grows forever. Notes were capped, but Recent issues and Decisions listed everything ever logged, so on an aged project reading the memory cost more than reading the code. Every open issue is still shown — the newest 20 in full, older ones by id — while fixed issues are capped at the newest 10 and decisions at the newest 15, each with a line saying what was left out and where to find it. On a test project with 25 issues and 60 decisions the summary went from about 2,900 tokens to about 1,100. (#19)

Commits are filed under the code they change. Auto-capture used the first changed path in git's sort order, which was usually the regenerated .projectmem/summary.md — so valid memories were flagged stale and the real file lost its history. The location is now the source file the commit is about, with deletions, renames, merges and a repository's first commit handled. (#20)

Stale warnings no longer depend on your time zone. A 0.3.3 speed-up compared git's local-time commit dates with UTC event times as text: west of UTC, recent stale memories were never flagged; east of UTC, fresh ones were flagged at once. Both sides are compared in UTC now, and events already filed under .projectmem/ stop warning without your log being rewritten.

*