Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Repository Index
47,133 repositories indexed
1–15 of 15 · Most stars
Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.
- claude
- claude-code
- claude-code-plugins
- mcp
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
- cloudflare-pages
- cloudflare-workers
- drizzle-orm
- tailwindcss
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
- agent
- agentic-rag
- ai-coding
- code-search
🌌 A complete search engine and RAG pipeline in your browser, server or edge network with support for full-text, vector, and hybrid search in less than 2kb.
- data-structures
- full-text
- search
- typo-tolerance
Tiny and powerful JavaScript full-text search engine for browser and Node
- fuzzy-search
- javascript
- search
- fulltext-search
Sync-in · Sovereign platform for file storage, sharing, synchronization, and collaboration.
- self-hosted
- cloud-alternative
- collaboration
- collaborative-editing
An open source headless CMS / real-time database. Powerful table editor, full-text search, and SDKs for JS / React / Svelte.
- rdf
- linked-data
- rust
- server
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
- mcp
- mcp-server
- mongodb
- mongodb-atlas
A fast, local-first Notion alternative built with Rust + Tauri. Block editor, nested pages, full-text search, black-and-white UI, ~115 MB RAM.
- desktop-app
- local-first
- notes
- notion-alternative
:mag: Data pipeline for crawling PDFs from the Web and transforming their contents into structured data using AWS textract. Built with AWS CDK + TypeScript
:mag: Full text indexing and searching library
- search-engine
- javascript
- typescript
- full-text-search
OpenMinutes · 录音笔工作台：MemoTalk S1 录音的导入 · 转录 · AI 归类 · 检索复盘（Floatboat Workbench 开源实现）
- ai-classification
- floatboat
- react
- speech-to-text
Example showcasing how to use Prisma + Postgres + Jest, where each test has its own unique DB context
acquire a fresh docker database container attached to your ava test context