Category

VibeTunnel

Forwards local terminal sessions to any web browser, so you can watch and steer long-running CLI processes — including AI coding agents like Claude Code — from a phone or another machine. A macOS menu-bar app proxies PTY output over WebSocket.

Project N.O.M.A.D.

Offline-first knowledge server that bundles local AI chat (Ollama + vector RAG), offline Wikipedia/education/maps, and utility tools behind a Dockerized management UI — designed to keep searchable knowledge available without cloud access.

MonkeyCode

Browser-based AI development platform that runs tasks inside isolated cloud development environments: natural-language agents read code, run commands, modify files, and integrate results back into Git. Key features include per-task sandboxes, multi-model selection, and an enterprise private-deploy option.

LEANN

Stores a pruned proximity graph instead of all embeddings, recomputing vectors on demand at query time. A 60M-doc index takes 6GB, not 201GB (97% less), at comparable recall. Powers private local RAG over files, mail, chat, and browser history.

AngelSlim

Model-compression toolkit for large LLMs/VLMs that integrates quantization (FP8/INT4/etc.), speculative decoding, token pruning and deployment hooks—designed for end-to-end performance on single/multi-GPU inference workflows and research-to-prod model optimization.

OpenRAG

Bundles Langflow, Docling, and OpenSearch into one installable package so you can ingest messy documents, run agentic retrieval with re-ranking, and chat over your own knowledge base. Ships Python/TS SDKs and a built-in MCP server at /mcp.

WeKnora

Turns enterprise documents into RAG Q&A, autonomous reasoning agents, and self-maintaining wiki pages, with multi-source ingestion, RBAC, observability, and self-hosted deployment.

Memori

An open-source memory layer that turns agent runs and conversations into structured, persistent state recallable across sessions. Captures facts, events, preferences, and relationships automatically; LLM-agnostic with SDK and MCP integration.

memU

Compiles an agent's raw chat logs, documents, and tool traces into three persistent layers — index, learned skills, and user memory — so context survives sessions. Claims 92% Locomo-benchmark accuracy and up to 95% lower token cost than replaying history.

InsForge

Lets AI coding agents provision and operate a full backend themselves — Postgres with pgvector, OAuth2 auth, S3-style storage, Deno edge functions, and hosting — through one interface, plus an OpenAI-compatible model gateway.

FFF

Provides a long‑lived, in‑process file and content search library for editors and AI agents, with typo‑resistant fuzzy matching, frecency‑ranked results, background watchers, and a lightweight in‑memory content index — optimized for repeated searches in long‑running processes.

Mini-SGLang

A ~5,000-line Python LLM inference engine that re-implements SGLang's serving optimizations — radix KV-cache reuse, chunked prefill, overlap scheduling, tensor parallelism — as a fully type-annotated reference instead of a black box.