Skip to main content

Record and search your AI chat history. Markdown files, zero dependencies beyond MCP.

Project description

OpenClaw Memory

Your AI conversations disappear after every session. OpenClaw Memory fixes that.

Every time you chat with an AI coding assistant, valuable context — decisions, solutions, debugging steps — vanishes when the session ends. The next session starts from zero.

OpenClaw Memory automatically records every conversation turn to local Markdown files, making your entire AI chat history searchable and browsable. No cloud, no database — just plain text files in your project.

How It Works

You chat with AI  →  Every turn auto-saved to .openclaw_memory/journal/2026-02-24.md
                  →  Search past conversations via MCP tool or web viewer

Each journal entry captures the complete conversation: timestamps, model used, your input, the AI's full response, and any code changes made.

Quick Start

1. Install

pip install claw-memory

2. Initialize in your project

cd your-project
claw-memory init

This creates:

  • .openclaw_memory/journal/ — where chat history lives
  • .cursor/mcp.json — connects the MCP server to Cursor
  • .cursor/rules/memory.mdc — tells the AI agent to auto-record

3. Restart Cursor — that's it. Every conversation is now being recorded.

Searching Past Conversations

The AI agent can search your history automatically. Just ask naturally:

"We discussed this before, what was the solution?"

"Last time we fixed a similar bug, how did we do it?"

The agent will call memory_search() behind the scenes and find matching conversations.

Search via Web Viewer

claw-memory web

Opens a browser-based viewer where you can:

  • Browse journal files by date
  • Full-text search across all conversations
  • Dark/light mode

What Gets Recorded

Each conversation turn is saved as Markdown:

## 14:32 | claude-4-opus

### User

How do I fix the N+1 query problem in the user list endpoint?

### Agent

The issue is in `api/users.py` where each user triggers a separate query for their roles...

### Code Changes

- `api/users.py` (modified)
- `tests/test_users.py` (modified)

MCP Tools

Tool Purpose
memory_log_conversation Record a complete conversation turn
memory_log_conversation_append Append to the last turn (for long responses)
memory_search Search chat history by keyword

Storage

All data is stored locally in .openclaw_memory/journal/ as plain Markdown files — one file per day. No database, no cloud sync. You own your data.

The .openclaw_memory/ directory is auto-gitignored to prevent accidental commits of chat history.

Project Isolation

Each project gets its own .openclaw_memory/ directory. Searching in project A never returns results from project B.

License

Apache 2.0

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

claw_memory-1.0.1.tar.gz (177.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

claw_memory-1.0.1-py3-none-any.whl (18.8 kB view details)

Uploaded Python 3

File details

Details for the file claw_memory-1.0.1.tar.gz.

File metadata

  • Download URL: claw_memory-1.0.1.tar.gz
  • Upload date:
  • Size: 177.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for claw_memory-1.0.1.tar.gz
Algorithm Hash digest
SHA256 c59501ddb0913922ec9c8d63b4ded46cd94d7082f1163588f632af659dd1dd53
MD5 9a35a9fed9a542d5e8cc587529edb17f
BLAKE2b-256 7891e7b69b86d78b2928297e4b9a0b9e762add7992b043575bf4790b1b35e90c

See more details on using hashes here.

File details

Details for the file claw_memory-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: claw_memory-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 18.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for claw_memory-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 0b4eeb6843044f39c980184f04261d24d58c8ebbaef4dd5ed021e6435d2d2e7d
MD5 f6a99269aae58def51b2df56d747462a
BLAKE2b-256 56aba2517385b32e4ee0d92c964658d976976d1b075c155df2095df5d645ec6d

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page