deja-vu
Reduces redundant agent work and context overhead by enabling agents to search prior solutions without LLM calls, lowering latency and token costs while main…
Your agents already solved this. deja finds it — memory operations for fourteen coding agents: retroactive search and MCP recall (84.9% R@1 on LongMemEval-S, no LLM), trust scopes, curated notes with tags and lifecycle states, measured impact. One zero-dep binary, fully local.
- Ask Claude to search previous agent solutions when facing similar coding problems.
- Generate tagged notes from past agent work to avoid re-solving identical issues.
- Find high-impact code patterns your agents discovered across fourteen different projects.
Reduces redundant agent work and context overhead by enabling agents to search prior solutions without LLM calls, lowering latency and token costs while maintaining solution consistency across teams.
Engineering teams deploying multi-agent coding systems that need persistent cross-agent memory and fast solution retrieval.
https://github.com/vshulcz/deja-vu
By vshulcz
How to Get It
claude plugins install vshulcz/deja-vu
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.
After installing, paste this into Claude:
Search previous agent solutions when facing similar coding problems
Trust Signals Auto-scanned
Community Pulse New
- Dejavu: Audio fingerprinting and recognition in Python — Hacker News · 170 pts
- DéjàVu: a map of code duplicates on GitHub — Hacker News · 134 pts
- Open-source memory for coding agents, synced over SSH — Hacker News · 131 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 458 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 458 GitHub stars; contributors unknown; last commit 0d ago; license MIT.