#238238th of 389 in Skills, plugins and prompts
deja-vu
Local search and cross-agent handoff over session histories of 43 coding agents
- Stars
- 1.5k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Go
11 on 14 Jul 20261,511 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
deja indexes the session transcripts that coding agents such as Claude Code, Codex, Cursor and OpenCode already write to disk, and makes them searchable from a CLI, a terminal UI, or MCP and hooks. It can hand a session's goal and state to another agent, restore code an agent overwrote before commit, and attribute lines to sessions. It is a single Go binary with a local index, no LLM calls, and credential redaction at index time.
Who it is for: Developers who use several coding agents and want shared, local memory
Strengths
- Indexes existing transcripts from 43 agents, so history is searchable on day one
- Single Go binary; indexing and search are local with no LLM calls
- Handoff, restore and blame commands cover recovery cases beyond plain search
- Redacts credentials at index time; benchmark drivers and corpora are in the repo
Weaknesses
- Source transcripts keep secrets unless you run deja secrets --scrub
- Install script is shell-only; Windows needs Scoop, winget or a zip
- Semantic search needs a configured embedding endpoint, which receives each query
- Benchmark claims are self-published against other memory tools
What it needs
- no GPU
- Docker
Quick answers
Is deja-vu open source?
Yes. Its code is on GitHub under the MIT license.
Can you run deja-vu with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |