Agent-agnostic memory layer — one memory store for every AI agent.
Project description
AgnoMem
Agent-agnostic memory layer — one memory store for every AI agent.
Claude forgets when you create a new account. GPT-4 has no idea what Claude learned. Cursor and your scripts live in completely separate memory silos. AgnoMem fixes this: a single local memory server that every AI agent reads from and writes to automatically.
pip install agnomem
export OPENAI_API_KEY=sk-... # or ANTHROPIC_API_KEY
agno install
That's it. Claude Code, Cursor, Windsurf, and your own Python scripts now share the same memory.
How it works
Your AI Agents (Claude, GPT-4, Cursor, custom scripts)
│
▼
AgnoMem server (localhost:7832)
│
▼
Mem0 + ChromaDB (persisted at ~/.agnomem)
agno install— installs Mem0, starts the server, injects instructions into Claude Code'sCLAUDE.mdand your editor's rules file- SDK patch — two lines in your Python script and every
anthropic/openaicall gets relevant memories prepended to the system prompt automatically - Portable — all data lives in
~/.agnomem. Export, backup, or move it anywhere.
CLI
agno install # full setup in one command
agno start / stop / status # server management
agno search "how do I deploy?" # semantic search over memories
agno remember "use fly deploy" # write a memory
agno list # list all memories
agno inject --project # inject into current project's editor rules
agno eject # remove all injections cleanly
Python SDK
import agnomem
agnomem.enable() # patches Anthropic + OpenAI SDKs — call once at startup
import anthropic
client = anthropic.Anthropic()
# every subsequent call automatically gets relevant memories in the system prompt
Requirements
- Python 3.10+
OPENAI_API_KEYorANTHROPIC_API_KEY(Mem0 uses an LLM to extract facts)
License
MIT
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agnomem-0.1.0.tar.gz.
File metadata
- Download URL: agnomem-0.1.0.tar.gz
- Upload date:
- Size: 12.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
49119338b17de888e8b8ce398dc5d20476ea4a707b2604558629f687820e2cb2
|
|
| MD5 |
40b0138ed494545311cc113a1bf8e9f7
|
|
| BLAKE2b-256 |
45aa2131109e3350265f135c240e40db2445ace28cdf252f245a59f9c906e4bf
|
File details
Details for the file agnomem-0.1.0-py3-none-any.whl.
File metadata
- Download URL: agnomem-0.1.0-py3-none-any.whl
- Upload date:
- Size: 14.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
83df8258ffb53588ab7b0b0bcec6d1ce06cb441ece54584e9fa4b66c46d926cf
|
|
| MD5 |
f6d0bae75ddda4088544216c386d3746
|
|
| BLAKE2b-256 |
c36e3256769d5f7c1b950a54216566302863607f97815daa368b1461a9c8012b
|