ai-memory vs okf-agent-memory
Rust long-term memory server for coding CLIs: lifecycle hooks capture sessions into a sanitized shared wiki, then hand a bounded summary to the next agent so Codex can resume what Claude Code started. — versus — Git-native agent memory on Google's OKF v0.2: Markdown+YAML concepts in knowledge/, a zero-dep Go CLI/MCP with <300µs BM25 search, provenance and trust tiers.
ai-memory captures sessions into a shared wiki via hooks and serves it from a Rust server; OKF is the opposite posture — deliberate, reviewed concept authoring with no capture pipeline and no daemon.
| ai-memory | okf-agent-memory | |
|---|---|---|
| Stars | 6.4k | 542 |
| Forks | 440 | 33 |
| Language | Rust | Go |
| License | MIT | MIT |
| Last activity | 2 days ago | yesterday |
| Topics | memory, coding | memory, coding, knowledge-graphs |
| Curated connections | 8 | 5 |
ai-memory — the curator's take
The strongest bet if you genuinely switch harnesses mid-task: hook and MCP installers for roughly fifteen CLIs, a portable event ledger, `ai-memory run <harness>` for managed cross-vendor resume, and one Rust binary you can systemd. You pay for that reach in surface area — per-harness caveats matter (several CLIs discard SessionStart stdout, so handoffs come back through MCP `memory_handoff_accept`; Codex and Kiro need an explicit `finalize-session`), and you configure capture exclusions plus LLM and embedding providers. If you live in exactly one harness, a single-harness plugin gets you 80% of this with a tenth of the setup.
okf-agent-memory — the curator's take
Pick this when you want agent memory you can `git diff` and code-review: every concept is a Markdown file with provenance, trust tier and staleness metadata, and progressive-disclosure indexes keep loads small. It is lexical-only (BM25) by design — no embeddings, no API cost — so it wins on decisions, constraints and glossary-style facts, not on fuzzy semantic recall of past conversations. Skip it if you want automatic session capture (it is search-before-write, human/agent-authored) or memory shared across many repos; it is per-project and lives in the repo.