Your AI Agent Remembers Things. Who Audits What It Remembers?
The problem nobody talks about AI agents are getting persistent memory. mem0, Zep, Letta, Cognee — they all store what your agent "learned." But none of them answer three questions: Who wrote this fact? (which agent, which session) What did it replace? (when the agent changed its mind) Can someon
AI agents are getting persistent memory. mem0, Zep, Letta, Cognee — they all store what your agent "learned." But none of them answer three questions:
If your agent makes decisions based on remembered facts, these are governance questions. And governance without evidence is just hope.
MemTether is a local-first memory hub where:
| | Plain markdown | MemTether | |---|---|---| | Who wrote this? | ❌ | ✅ source + timestamp | | What did it replace? | ❌ overwritten | ✅ supersession chain | | Tamper detection | ❌ | ✅ hash chain | | Concurrent write safety | ❌ last-write-wins | ✅ file lock + WAL | | Query past states | ❌ | ✅ as_of("2026-10-15") | Enter fullscreen mode Exit fullscreen mode Export to markdown anytime — but keep the governed database as the source of truth.
All results from our own harness with per-question records committed to the repo. We documented a 27× score inflation from mixed denominators in memory benchmarks — which is why we report each metric under the exact scoring rule that produced it.
pip install memtether memtether demo memtether search "投影" --list Enter fullscreen mode Exit fullscreen mode Works with Claude Code, Codex, Cursor, and 20 other agents via file-level pointers or MCP.