agent-beacon vs deja-vu
Cross-harness memory for coding agents: captures sessions from Claude Code, Cursor, Codex and 20+ harnesses, distills reviewed knowledge over MCP/skills, and forwards telemetry to SIEMs. — versus — Indexes the session histories your coding agents already wrote — 17 harnesses, months retroactive — and serves recall over MCP. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One Go binary.
Both mine the session histories coding agents already write across many harnesses and serve recall over MCP; deja-vu is one Go binary with no LLM or embeddings, Beacon adds reviewed knowledge, exact replay and SIEM forwarding.
| agent-beacon | deja-vu | |
|---|---|---|
| Stars | 1.7k | 1.1k |
| Forks | 145 | 104 |
| Language | Go | Go |
| License | MIT | MIT |
| Last activity | today | today |
| Topics | memory, coding, security | memory, coding |
| Curated connections | 3 | 8 |
agent-beacon — the curator's take
Two jobs in one endpoint agent, and it pays to know which one you want. The memory side captures every session across Claude Code, Codex, Cursor, OpenCode and 20+ harnesses, replays them exactly, and turns fixes and conventions into reviewed knowledge future agents pull through MCP or Agent Skills. The security side normalizes the same traces into an OpenTelemetry event model and ships them to Splunk, Sentinel, CrowdStrike LogScale and friends, with MSI, .deb/.rpm and MDM installs. Strong fit when a team runs many harnesses and wants one record for both recall and audit. Watch the default: interactive setup preselects hosted Beacon Managed forwarding (Local is an explicit opt-out), so choose deliberately on machines with sensitive code. For solo, single-harness recall, claude-mem or deja-vu is less machinery.
deja-vu — the curator's take
The inversion is the insight: every memory tool starts empty and records forward; deja starts FULL from history already on disk, and the no-LLM/no-embedding design means ~1.5ms search, zero keys, zero cost. When NOT: it remembers what your agents did, not curated knowledge — there's no write path for distilled lessons; and its benchmark numbers are self-published, so the standing caution on this shelf applies: benchmark recall on your own corpus.