TrueMemorySAFE
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
–
–
Why · Quick Start · Compare · Tiers · Benchmarks · API · Docs · FAQ · Discord
Why TrueMemory
It finds signal in the noise. Your AI sees thousands of messages. TrueMemory figures out which ones actually matter and throws away the rest. No manual tagging,
8f12b842c095OBSERVED · 2026-10-02Connect
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 truememory-openclaw-plugin --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env GROQ_API_KEY=${GROQ_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env OPENROUTER_API_KEY=${OPENROUTER_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"truememory-openclaw-plugin": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"GROQ_API_KEY": "${GROQ_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"OPENROUTER_API_KEY": "${OPENROUTER_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
TrueMemory | read | TrueMemory persistent memory integration for OpenClaw |
Trust audit
SAFEgrade B · trust 83/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (7 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
AppIcon.icns
mod = __import__(mod_name, fromlist=["_TRUEMEMORY_DIR"])
mod = importlib.import_module(f"truememory.ingest.hooks.{name}")mod = importlib.import_module(module)
mod = importlib.import_module(module)
mod = importlib.import_module(module)
return struct.unpack("<I", hashlib.md5(s.encode("utf-8"), usedforsecurity=False).digest()[:4])[0]assert _sanitize_session("../../../etc/passwd") == "etcpasswd"core.buffer_message("../../etc/passwd", "exploit attempt")assert _sanitize_session_id("../../etc") == "etc"mp.setenv("TRUEMEMORY_CUSTOM_EMBED_MODEL", "../../../etc/passwd")base_url="http://192.0.2.1:1",
assert len(bytes.fromhex(token_hex)) == 32
recovered = bytes.fromhex(token_path.read_text().strip())
data = base64.b64decode(obj["__ndarray__"])
token = bytes.fromhex(TOKEN_PATH.read_text().strip())
data = base64.b64decode(obj["__ndarray__"])
openai, modal, rank-bm25, engram-core, mem0ai, sentence-transformers, truememory, sentence-transformers
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
curl -LsSf https://raw.githubusercontent.com/buildingjoshbetter/TrueMemory/main/install.sh | sh
benchmarks/beam/truememory_pro_beam1m_run1.json
benchmarks/beam/truememory_pro_beam1m_run2.json
Gates applied: no_behavioural_pass.
8f12b842c095full audit observations/trust-audit/mcp-server/buildingjoshbetter__truememory.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 |
|---|---|---|---|---|---|
| 2026-10-02 | 8f12b842c095 | SAFE | B | 83 | first audit |
Questions
What is the TrueMemory MCP server?
The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.
What tools does TrueMemory expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is TrueMemory safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (83/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does TrueMemory need?
It reads ANTHROPIC_API_KEY, GROQ_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY and SUPERMEMORY_API_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 TrueMemory run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as truememory-openclaw-plugin at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (8f12b842c095), read on 2026-10-02. The repository is watched and re-audited when it changes.