DanceNitra/inspeximus

**Tamper-evident long-term memory for AI agents. Correct a fact once and the old value stays retired; erase a person and prove it; show an auditor what the agent knew when it acted. One zero-dependency Python file, plus an MCP server.**
The erasure proof covers this store only, not a vector index, prompt logs, or backups, and it is an integrity primitive, not a compliance certification.
Quickstart ·
Docs ·
vs mem0 and Graphiti ·
Migrate from mem0 ·
EU AI Act and GDPR evidence ·
Claude Code, one line ·
Transparency log ·
PyPI
memory.json is a name, not a format: a new store is a SQLite file. Read it through inspeximus or the
sqlite3 module, never with json.load or cat.
| | What you get |
|---|---|
| **A correction that holds** | remember(key=...) retires the old value by key. Restating the stale text does not bring it back; revert() does, as a recorded decision. |
| **Erasure you can prove** | forget_subject() removes every record about a person, leaves a signed content-free tombstone, and erasure_certificate() lets a third party check it with no private key. For authorship, the third party pins your public key (expected_pubkey) and witnesses the anchor. It covers this store only. |
| **What the agent knew when it acted** | A signed, hash-chained action ledger; matches() binds a retained transcript to its entry. |
| **When it happened** | RFC 3161 timestamps, and a check whether the authority was on the EU trusted list on that date. |
| **Evidence an auditor can read** | inspeximus compliance labels the evidence by article; export as a draft-sharif-agent-audit-trail-04 file. |
| **Any agent, one line** | MCP server for Claude Code, Cursor, Windsurf, Codex and Cline; adapters for LangChain, LangGraph, ADK and more. |
---
Why inspeximus
Use it when the agent runs for days and the facts it holds will change under it, and when
somebody can later ask what it knew and what it erased. That is the whole design brief.
| You have | Reach for |
|---|---|
| An agent that keeps confidently repeating a value you already corrected | remember(key=...): the correction wins, the restatement does not bring the old value back, revert() is a recorded decision |
| A right-to-erasure request, or an auditor asking what the agent knew when it acted | forget_subject() with erasure_certificate(); the signed action ledger with matches() |
| Claude Code, Cursor, Windsurf, Codex or Cline, and no memory between sessions | the MCP server, one config line |
| A framework (LangChain, LangGraph, ADK, Hermes, Haystack) and no way to prove a memory write happened | the adapters and the receipt chain |
**agno is the one that is not ours.** It ships an official integration example in its own
cookbook, cookbook/11_memory/integrations/inspeximus_integration.py,
merged in agno#10146 on 2026-09-20, alongside
mem0, zep, memori and dakera. Their own README describes it as *"inspeximus for
corrections that stay corrected."* We did not write that file's home and we do not maintain
it, which is exactly why it is worth listing: it is one integration a reader can check
without taking our word for anything. The same holds for agmi,
an agent-memory integrity scorecard whose maintainer merged our three-row adapter,
agmi/adapters/inspeximus_rows.py,
in agmi#1 after reproducing it himself.
Not the right tool when you want a hosted service with a dashboard, a knowledge graph over
documents, or the highest score on a conversational-recall benchmark. mem0, Zep and cognee lead
there, and the comparison page says where
each of us wins and where we do not.
The receipts
We measured the one thing the others do not publish: **how often a corrected fact comes back.**
Each system was run on its own native configuration, same task, same 30 trials:
| system | keeps the correction | resurrects the old value |
|---|---|---|
| **inspeximus** | **100%** | **0%** |
| Graphiti 0.x (Neo4j + OpenAI) | 86.7% | 13.3%   95% CI [3.3, 26.7] |