vshulcz/deja-vu
Coding agent memory for Claude Code, Codex, Cursor and 40 more, built from the session history already on your disk. Local search, MCP and hooks, no LLM, one Go binary.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
5 releases in the last 90 days, the latest today, with 82 contributors on GitHub.
Peaked at #55 in the weekly ranking the week of Sep 20, its best in the past year.
Use Cases & Benefits
- Provides a unified, searchable memory layer for coding agents by indexing their local session histories from multiple AI agents on disk.
- Enables instant, retroactive recall of past coding decisions across different agents without requiring an LLM, ensuring fast, accurate, and privacy-preserving memory access.
- Use for integrating seamless cross-agent memory recall in AI coding assistants to avoid redundant debugging and rework.
- Use for local, privacy-focused indexing and search of extensive coding session histories with automatic redaction of sensitive data.
- Use for synchronizing and sharing coding session memories securely between multiple machines without cloud dependency.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
- Contributing guide: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
The one memory your coding agents share, built from the history already on your disk.
Your agent is about to re-debug something you fixed in March — in a different agent. deja indexes the sessions Claude Code, Codex, Cursor and every other agent on this machine already wrote to disk, and hands the right one back in whichever agent asks.
Nobody searched anything — the agent called deja itself. Every line is quoted from two real sessions.
Every memory tool starts empty and records forward. deja starts full.
And nobody has to ask for it: recall arrives at session start, on every prompt, before a file is edited or a command runs, and after one fails. Keys and tokens are stripped as the index is built, so what reaches the model is safe to send.
85.3% hit@1 on LongMemEval-S · 69.7% on LoCoMo · millisecond lookups over gigabytes of history
Both harnesses ship in this repo and run on the public datasets in minutes · check the numbers yourself
Ten seconds to install, about ten to index, and it is useful. The second command wires MCP recall into every agent it finds, turns on session-start recall where the agent supports it, and builds the first index so the next session does not pay for it.
Start a new agent session and ask it something you worked on months ago:
have we dealt with jwt refresh rotation before? check your memory
It does not have to be asked, either — with auto-recall the agent already knows what you solved in that project when the session opens.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+445 stars over 40 days across 9 snapshot days; best day +36 on Sep 26.
Forks
157+70
Open issues
26-7
Compared with peers in LLM
Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| thedotmack/claude-mem | 113.6K | +8.8K | 35 | today |
| NVIDIA/auto-ontology | 7.5K | +5.6K | 37 | — |
| HKUDS/DeepTutor | 55.5K | +5.5K | 65 | 5 days ago |
| affaan-m/ECC | 297.9K | +5.2K | 63 | 35 days ago |
| DietrichGebert/ponytail | 185.3K | +5.1K | 60 | 7 days ago |
| vshulcz/deja-vu | 1.3K | — | 40 | today |
| Category median | 113.6K | +5.5K | 60 | — |
Discover Repositories
Search across tracked repositories by name or description