Portable, governed, model-agnostic memory for AI agents: facts invalidated never deleted, raw text as truth, one documented export format.
View on GitHub ↗Homepage ↗Al Buddy — that's Al, a name, said like "pal". Not A.I.
Portable, governed, model-agnostic memory for AI agents.
A fact is invalidated, never overwritten; on a governed handle, erasure runs through policy and is audited. Raw text is the source of truth and cannot be edited. Embeddings are a disposable, model-tagged cache. Every fact and every link exports to one documented format. The memory outlives whatever model, runtime or company produced it.
Every agent-memory product on the market answers one question well: what does the agent recall? None of them answers the four questions that decide whether you can trust and keep that memory:
Question This library Letta Mem0 Zep --------------- Where did this fact come from, and who asserted it? Provenance on every node and edge (UserInput / AIInferred / GuardianAdded / SystemGenerated) Memory-file git history Metadata field Graph episodes When was it true, and what replaced it? validFrom / validTo (valid time) plus append-only anchors (when the store touched a fact); a validAt query answers "what was true at X". It does not yet answer "what did we believe at X": an update records that a change happened, not the prior value Git history of files, not a fact model No Temporal graph (its real strength) Can I take it with me, losslessly, to another runtime? One versioned JSON export with a published schema and conformance tests .af (agent state, framework-shaped, archival memory not yet included) Cloud export Cloud-only since 2025 Does it run with no vendor, no key, no server? SQLite on disk, on-device embeddings Self-host possibl
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/flytomoon--al-buddy-memory.html)
Typed long-term memory for AI agents. One core, an MCP server, and a Hermes plugin.
menot-you/n-memoryMemory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
holetexvn/memgwShared long-term memory for AI coding agents — one local store for Claude Code, Codex CLI, opencode and anything that speaks MCP. SQLite + FTS5, no vector DB, $1-3/month.
motif-Labs/motifCoding agents are single-player: each session starts cold, in its own tool, blind to what the rest of the team already worked out. Motif makes your team's multiplayer — every Claude Code, Codex and Cu
adityajha2005/decisionkitFast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
osaxyz/sepiaceLong-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.