OMEGACAUTION
Persistent memory for AI coding agents
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Cross-model memory for AI agents. Local-first. Works with Claude, GPT, Gemini, Cursor, Claw Code, and any MCP client. Your agent's brain shouldn't live on someone else's server, or be locked to one provider.
[](https://www.python.org/downloads/) [](https://pypi.org/project/omega-memory/) [](LICENSE)
The Problem
AI coding agents are stateless. Every new session starts from zero. The "solutions" either lock you into one model provider or send your codebase context to their cloud.
- Context loss. Agents forget every decision, preference, and architectural choice between sessions. Developers spend 10-30 minutes per session re-explaining context that was already established.
- Repeated mistakes. Without learning from past sessions, agents make the same errors over and over. They don't remember what worked, what failed, or why a particular approach was chosen.
- Cloud memory = someone else's database. Services like Mem0 require API keys and send your data to their servers. When they change pricing, get acquired, or go down, your agent's accumulated intelligence disappears.
- Vendor lock-in. Anthropic's Memory Tool only works with Claude. OpenAI's memory only works with GPT. Switch models, lose your memory.
OMEGA solves this. Memory, coordination, and learning that runs entirely on your machine. Works with every major LLM and coding agent. No cloud. No API keys. No vendor lock-in.
Quick Install
OMEGA needs Python 3.11 or newer. Check with python3 --version: macOS ships Python 3.9, which is too old. If pip answers No matching distribution found for omega-memory, that is the reason; install a newer Python first (
87f63eb76e9aOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add omega-memory -- None omega-memory==1.4.6
Trust audit
CAUTIONgrade C · trust 72/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (3 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- pinned
- Secrets in source
- found
Findings (17)
mod = importlib.import_module(script_name)
_sm = importlib.import_module(_schema_mod)
_hm = importlib.import_module(_handler_mod)
"tests/test_thing.py": 'api_key = "test-secret-value-not-real"\n',
("omega/credentials.pem", "-----BEGIN PRIVATE KEY-----\nprivate material\n-----END PRIVATE KEY-----"),hash_digest = hashlib.md5(text.encode()).digest()
cache_key = hashlib.md5(text.encode()).hexdigest()
digest = int(hashlib.md5(session_id.encode()).hexdigest()[:8], 16)
url = "http://127.0.0.1:8377/mcp"
with TestClient(app, base_url=f"http://127.0.0.1:{PORT}") as test_client:urllib.request.urlopen(f"http://127.0.0.1:{port}/health", timeout=1)url = f"http://127.0.0.1:{port}/mcp"Follow the protocol it returns
assets/demo.gif
assets/social-preview-gemini.png
assets/social-preview-new.png
Gates applied: no_behavioural_pass.
87f63eb76e9afull audit observations/trust-audit/mcp-server/omega-memory__omega.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 87f63eb76e9a | CAUTION | C | 72 | first audit |
Questions
What is the OMEGA MCP server?
Persistent memory for AI coding agents
Is OMEGA safe to connect to an agent?
With care. The audit graded it C (72/100) and found 17 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does OMEGA need?
It reads ANTHROPIC_API_KEY, OMEGA_LLM_API_KEY, OPENAI_API_KEY and SUPABASE_SERVICE_ROLE_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does OMEGA run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as omega-memory.
How current is this page?
The grade is for one exact copy of the source (87f63eb76e9a), read on 2026-10-06. The repository is watched and re-audited when it changes.