By hthsolid
Recover deleted Claude Code sessions, search past conversations via hybrid Postgres+Weaviate recall, list recent sessions, and ground AI code suggestions against indexed project symbols (tree-sitter across Python/TS/JS/Go/Rust/etc.), API routes (Express/FastAPI/Next.js), DB schemas (Prisma/Drizzle), env vars, flags, GraphQL types, and page paths to lint fabrications, suggest fixes, and rewrite with 89% hallucination reduction before disk writes.
npx claudepluginhub hthsolid/claude-dejavu --plugin claude-dejavuRead or change claude-dejavu settings (lint mode, auto-reindex, scope defaults, …)
Check or browse database schema (Prisma / Drizzle / TypeORM / SQL) — catches typos and fabricated table/column references
Diagnose claude-dejavu install + runtime health (Postgres, Weaviate, venv, hooks, symbol index)
Check or list environment variable declarations — catches fabricated names + typos in process.env / os.getenv reads
Use the claude-dejavu plugin's per-project fabrication memory to
Check or browse feature flag declarations (flags.json, feature-flags.ts, LaunchDarkly, Unleash, GrowthBook) — catches typos and fabricated keys
Check or browse GraphQL schema (SDL files + inline gql template literals) — catches typos and fabricated fields in queries / mutations
Lint a proposed file edit against the symbol index — flag fabricated names + typos before write
Use the claude-dejavu plugin's centralized error log to inspect
Show who built claude-dejavu, the project's mission, and how to get in touch
Run the `claude-dejavu outcomes` CLI to inspect the lint/lookup outcome
Check or list frontend page routes (Next.js / Remix / SvelteKit / Astro / React Router / Vue Router) — catches duplicate-page creation
Run the `claude-dejavu reindex` CLI to (re)build the symbol index for
List or restore deleted Claude Code session .jsonl files from the off-tree backup
Find the best matching past Claude Code session and produce a ready-to-run resume command
Resolve, list, or look up HTTP routes in the project's API index (Express / FastAPI / Next.js / NestJS / Flask / Django / Hono / Fastify / Koa / OpenAPI)
Generate a runtime defense layer that wraps `process.env` /
Hybrid (BM25 + vector) search across past Claude Code sessions
Semantic search across symbols + routes by intent (cosine similarity via Weaviate embeddings)
Use the `dejavu_sessions` MCP tool from the claude-dejavu plugin to list
Resolve a code symbol against the project's indexed symbol database (catches hallucinated names)
Admin access level
Server config contains admin-level keywords
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Battle-tested Claude Code plugin for engineering teams — 53 agents, 203 skills, 69 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Modifies files
Hook triggers on file write and edit operations
Modifies files
Hook triggers on file write and edit operations
Share bugs, ideas, or general feedback.
Stop Claude from fabricating names. Restore deleted sessions. Search every past conversation.
Built by HTE Switzerland — a digital solutions partner shipping production AI infrastructure, full-stack development, and cloud-grade engineering.
Every Claude API call costs tokens. Every fabricated name (a made-up env var, a wrong field on a Prisma model, a typo of a route, a fictional GraphQL field) ends in a rewrite — and a second API call to fix the first one. claude-dejavu catches those fabrications BEFORE they hit disk.
Twelve languages, eight grounding domains: symbols (Python, TypeScript, TSX, JavaScript, Go, Rust, Java, Ruby, Bash, PHP, C#, Kotlin), HTTP routes, frontend pages, env vars (with an SDK convention catalog covering LaunchDarkly / AWS / Stripe / Sentry / Redis / Postgres / Next / Datadog / OpenAI / Anthropic / Supabase / …), DB schema (Prisma / Drizzle / TypeORM / SQL migrations), GraphQL (SDL + inline gql), feature flags (LaunchDarkly / Unleash / GrowthBook / flags.json), plus an LSP wire-protocol passthrough for type-check ground truth.
89.3% measured reduction in hallucinated identifiers. On a 400-trial controlled benchmark against claude-sonnet-4-6 (51.5% → 5.5%, McNemar exact p=9.6e-27, 95% CI 82.7–95.1%), claude-dejavu's grounding cuts fabricated names by 89.3%. In additional tests with v0.5.0a's 14-strategy deterministic rewriter cascade (n=200, same prompts and scoring), we've measured up to 99% reduction (51.5% → 0.5%) — that's the upper bound seen so far, not a stability guarantee. Treat 89.3% as the rigorous headline. See docs/REWRITER.md for the rewriter architecture and docs/benchmarks/ for both reports.
Plus session recovery. Claude Code stores every conversation in ~/.claude/projects/<encoded>/<uuid>.jsonl. Those files can be deleted, truncated, or otherwise lost — by Claude, by a stray git clean, by manual cleanup. claude-dejavu mirrors them so deletion never costs you the conversation. Semantic search across every past chat means "have we discussed X before?" now has an answer.
Both ship as a Claude Code plugin AND a standalone CLI:
Every Claude Code Stop event mirrors the live .jsonl to an off-tree location. When a session disappears from ~/.claude/projects/, the next time Claude Code runs you see this:
⚠ claude-dejavu: 3 session(s) missing from
~/.claude/projects/. Runclaude-dejavu restore --listto see all.
Then one command brings them back, byte-perfect, with a runnable claude --resume command:
$ claude-dejavu restore --list
Restorable sessions (3):
deleted aaaaaaaa-1111-0000-0000-000000000001 myproject 2026-04-15 124.7 MB
deleted aaaaaaaa-2222-0000-0000-000000000002 myproject 2026-04-08 25.3 MB
deleted aaaaaaaa-3333-0000-0000-000000000003 other-app 2026-04-02 0.9 MB
$ claude-dejavu restore --all
✓ aaaaaaaa-1111-… (124.7 MB) → ~/.claude/projects/-home-…/aaaaaaaa-1111-….jsonl
resume: cd ~/projects/myproject && claude --resume aaaaaaaa-1111-…
✓ aaaaaaaa-2222-… ( 25.3 MB)
✓ aaaaaaaa-3333-… ( 0.9 MB)
Restored 3/3 session(s).
Hybrid BM25 + vector search across every turn of every past session. By default returns ~80-token gists; expand specific turns on demand to keep token cost low.
$ claude-dejavu search "auth refresh token rotation"
scope=ws:my-stack hits=2
[1] turn=1842 score=0.84 myproject/aaaaaaaa-1111 2026-04-15
Refresh-token rotation: store hash, single-use, 5min grace window for clock skew…
[2] turn=2104 score=0.61 backend/bbbbbbbb-2222 2026-04-12
JWT exp 15m + refresh 30d, rotation on every use, revocation list in Redis…
Claude can call this automatically through the bundled MCP server, so when you ask "have we discussed auth?" mid-session, it grounds itself in your actual past conversations instead of inventing context.