mengram
Semantic, episodic, and procedural memory for AI agents, like human记忆被切断了，请稍后尝试重新生成。
GraphCanon updated 2w · GitHub synced 2w
Decision brief
Mengram offers memory functionalities tailored for AI agents, including semantic, episodic, and procedural capabilities with integrations into platforms like LangChain, CrewAI, and OpenClaw.
Good fit when
- Use Mengram if your project requires a comprehensive suite of human-like memory capabilities (semantic, episodic, procedural) for AI agents.
- Prefer Mengram when you need smooth integration into multiple platforms such as LangChain, CrewAI, and OpenClaw without the need to build custom connectors.
Avoid when
- Avoid Mengram if your project focuses solely on a specific type of memory (e.g., only semantic) and requires more specialized functionality not provided by Mengram.
- Mengram might be less appealing if direct terminal access is preferred over the provided one-prompt setup method, which some users might deem as more complex or cumbersome.
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (3d since push)
- As of 2w
- Provenance
- Not a fork · Personal account
- As of 2w
- Security (OSV)
- 23 low (23 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install mengramSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Offers memory capabilities for AI agents including semantic, episodic, and procedural memory with integrations into various platforms like LangChain, CrewAI, and OpenClaw. Provides Python and JS SDKs alongside a free API.
Capability facts
- Deploy
- Self-host
Source: dockerfile:docker-compose.yml · Aug 2, 2026
- Docker
- Dockerfile present
Source: dockerfile:docker-compose.yml · Aug 2, 2026
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 2, 2026
- MCP server
- No MCP server detected
Source: repo_scan · Aug 2, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 2, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 2, 2026)
Paste this into Claude Desktop, Cursor, Codex, Claude Code, or Windsurf — the agent reads our [setup guide](htSource link
Source: README excerpt (regex_v1, Aug 2, 2026)
Paste this into Claude Desktop, Cursor, Codex, Claude Code, or Windsurf — the agent reads our [setup guide](https://meSource link
Source: README excerpt (regex_v1, Aug 2, 2026)
Paste this into Claude Desktop, Cursor, Codex, Claude Code, or Windsurf — the agent reads our [setup guide](https://mengram.io/agent-install.txt), instSource link
Tags
README
Install in one prompt (any AI tool)
Paste this into Claude Desktop, Cursor, Codex, Claude Code, or Windsurf — the agent reads our setup guide, installs the SDK, configures the MCP server, and verifies the round-trip end-to-end. No terminal context-switching.
Install Mengram for me. Fetch the canonical install guide at
https://mengram.io/agent-install.txt and follow it precisely.
My email is YOUR_EMAIL_HERE.
Works in any agent with shell + file-edit + web-fetch tools. Prefer doing it manually? See the plain-text guide — it's structured for human eyes too.
2. Install the plugin (hooks + MCP server + skill)
claude plugin marketplace add alibaizhanov/mengram claude plugin install mengram@mengram
and Railway. Recently debugged pgvector deployment. Prefers direct
License
Apache 2.0 — free for commercial use.
Get your free API key · Built by Ali Baizhanov · mengram.io
For agents
This page has a .md twin and JSON over the API.