Stars
Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.
🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or…
A small desktop robot that brings an AI coding assistant to life, physically acting out when it reads files, thinks, writes code, and finishes work.
iOS IPA Decrypter for TrollStore
The batteries-included agent harness.
🙌 OpenHands: AI-Driven Development
Deletes all instances of Microsoft's GDID and prevents minting of new ones
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Your clothes, extracted and organized with gpt-image.
Source code for an online decrypted app on App Store, require M1 macOS running on 11.2.3 or lower
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code , Opencode durable memory — entirely offline.
Companion code for the global workspace interpretability paper
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
MCP Server that wraps mitmproxy and exposes it as a tool to any MCP client, allows your AI agents to inspect traffic, filter traffic, intercept & modify traffic, request reply, set global headers, …
Super basic implementation (gist-like) of RLMs with REPL environments.
General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.
Hindsight: Agent Memory That Learns
Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% l…
Realtime log viewer for containers. Supports Docker, Swarm and K8s.
Ready-to-run Docker Compose stacks for 120+ self-hosted apps, each with a Tailscale sidecar and automatic HTTPS
⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.
Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.