AGI MemoryBLOCK
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Memory, Identity, and the Shape of Becoming
[](https://github.com/QuixiAI/Hexis/actions/workflows/ci.yml) [](LICENSE) [](https://www.python.org/downloads/)
A Postgres-native cognitive architecture that wraps any LLM and gives it persistent memory, autonomous behavior, and identity. You run it locally. Your data stays yours.
LLMs are already smart enough. What they lack is continuity -- the ability to wake up and remember who they are, pursue goals across sessions, and say no because it contradicts something they've become. Hexis provides the missing layer: multi-layered memory, an autonomous heartbeat (the agent's own wake-up cycle), an energy budget, and a coherent self that persists over time.
What makes Hexis different from every other agent framework:
- A brain, not a vector store. Cognition lives in PostgreSQL — memory, beliefs, identity, goals, and energy are ACID state with the logic beside the data. Other frameworks bolt retrieval onto a chat loop; Hexis is a mind you can query.
- Beliefs that answer "why." Confidence rises and falls with evidence through an audited revision policy — the agent can tell you exactly which document moved a belief from 0.60 to 0.71, and when.
- A self, not a session. Identity, worldview, emotional state, drives, and an autonomous heartbeat that pursues goals while you're away — with an energy budget that keeps autonomy intentional.
- Your mind is a file.
hexis export --mindcreates a private, inspectable HMX file that can move to an empty machine and prove the same lineage and constitutional state woke up there. - **Learn
64f8864d0c41OBSERVED · 2026-10-07Connect
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 hexis-ui --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env ANTIGRAVITY_OAUTH_CLIENT_ID=${ANTIGRAVITY_OAUTH_CLIENT_ID} --env ANTIGRAVITY_OAUTH_CLIENT_SECRET=${ANTIGRAVITY_OAUTH_CLIENT_SECRET} --env ASANA_ACCESS_TOKEN=${ASANA_ACCESS_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"hexis-ui": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"ANTIGRAVITY_OAUTH_CLIENT_ID": "${ANTIGRAVITY_OAUTH_CLIENT_ID}",
"ANTIGRAVITY_OAUTH_CLIENT_SECRET": "${ANTIGRAVITY_OAUTH_CLIENT_SECRET}",
"ASANA_ACCESS_TOKEN": "${ASANA_ACCESS_TOKEN}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Chat | read | Open your conversation with Hexis |
Example | read | Description |
Hexis | read | A persistent AI identity, available wherever you are. |
Trust audit
BLOCKgrade F · trust 30/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (11 observation(s))
- Network
- declared (13 observation(s))
- Shell
- declared (8 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
b64decode( ... subprocess.
exec(code, namespace, namespace) # noqa: S102
exec(code, combined, combined)
if hostname in ("metadata.google.internal", "metadata.internal"):return f"postgresql://{db_user}:{db_password}@{db_host}:{db_port}/{db_name}"return f"postgresql://{user}:{password}@{host}:{port}/{database}"return f"postgresql://{self.user}:{password}@{self.host}:{self.port}/{self.database}"- Treat connection setup as a first-class conversation flow. Do not tell the user to leave chat and figure it out alone.
- Treat connection setup as a first-class conversation flow. Do not tell the user to leave chat and figure it out alone.
return importlib.import_module(_map[provider])
mod = importlib.import_module(entry[0])
["Local target", f"http://127.0.0.1:{payload.get('ui_port') or 3477}"],local_url = f"http://127.0.0.1:{port}/api/status"table.add_row("Endpoint", str(payload.get("url") or "http://127.0.0.1:42667"))or "http://127.0.0.1:43817"
hexis mcp --dsn postgresql://hexis_user:hexis_password@localhost:43815/hexis_memory
DATABASE_URL=postgresql://hexis_user:[email protected]:43815/hexis_memory
secret = "sk-supersecret123456"
token = "SECRETJOURNALTOKENZZ"
"private_key='-----BEGIN PRIVATE KEY-----\n"
monkeypatch.setenv("SLACK_BOT_TOKEN", "xoxb-test-token-value")assert result == "xoxb-test-token-value"
monkeypatch.setenv(token_env, "xoxb-test-token-that-is-long-enough")
monkeypatch.setenv(token_env, "xoxb-test-token-that-is-long-enough")
assert token == "xoxb-test-token-that-is-long-enough"
Gates applied: critical_finding, instruction_override, no_behavioural_pass.
64f8864d0c41full audit observations/trust-audit/mcp-server/cognitivecomputations__agi-memory-1.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 64f8864d0c41 | BLOCK | F | 30 | first audit |
Questions
What tools does AGI Memory expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is AGI Memory safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (30/100) and found 9 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does AGI Memory need?
It reads ANTHROPIC_API_KEY, ANTIGRAVITY_OAUTH_CLIENT_ID, ANTIGRAVITY_OAUTH_CLIENT_SECRET, ASANA_ACCESS_TOKEN, ASANA_API_KEY, CHUTES_CLIENT_SECRET, FATHOM_API_KEY, GEMINI_CLI_OAUTH_CLIENT_ID, GEMINI_CLI_OAUTH_CLIENT_SECRET, HEXIS_API_KEY, HEXIS_LLM_CONSCIOUS_API_KEY and HEXIS_WEB_PUSH_VAPID_PRIVATE_KEY_FILE 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 AGI Memory run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as hexis-ui at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (64f8864d0c41), read on 2026-10-07. The repository is watched and re-audited when it changes.