Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for AI engineering teams and power users who have months of Claude Code / Codex / Pi / Aider session history sitting in ~/.claude/projects, ~/.codex/sessions, and similar agent session ledgers and want a real deterministic MIT search engine over that history (no LLM, no embeddings, no API key), for any team that wants an MCP-exposed memory layer their existing agent harness can hit without
Where this stands now
vshulcz/deja-vu ranks #4 of 7 tracked Agent Memory items by composite score (8.2 against a section median of 8.2). The section currently carries 4 Silver, 3 Gold. RepoRadar has retained observations for this record since 2026-08-13 (58 days in the current window).
Who should use it
Who should skip it
Skip vshulcz/deja-vu if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
vshulcz/deja-vu is tracked by RepoRadar as a developer tool in the Agent Memory section. First seen 2026-08-13; the source record was last checked on 2026-08-13. The current verdict is 'try now' with a Silver tier and easy setup difficulty. The standout signals for vshulcz/deja-vu are workflow potential (9.7) and practical usefulness (9.0), while maturity (5.9) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.
How this item is evaluated
The vshulcz/deja-vu record combines a 8.2/10 composite score with separate popularity (0.6), risk (low), and setup (easy) signals. See the scoring methodology for the current weights and evidence definitions.
Questions worth asking before you adopt this
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Deja-vu reads the agent session ledgers under ~/.claude/projects, ~/.codex/sessions, and similar; the index includes session contents (user prompts, tool calls, file paths, code snippets) -- confirm the binary's data-handling posture and pin it to a single user account before enabling MCP exposure to a shared agent harness.