Aster
A self-hosted terminal coding agent that reads, edits, runs and reviews code on your machine, with your model and your key.
Local OpenAI LLM (Home Assistant Custom Integration)
Connect Home Assistant to any OpenAI-compatible LLM service — local or cloud — for Assist conversations, AI tasks, and retrieval-augmented generation.
rpi: Rust Coding-Agent Runtime
Build, run, and extend coding agents with an embeddable Rust runtime and a terminal CLI.
LightAgent
A lightweight Python runtime for OpenAI-compatible agents with tools, memory, routing, and recoverable workflows.
Chidori
A durable TypeScript agent runtime with checkpointing, replay, and resume built into every run.
GOD Agent Society Control Room
A local control room for replaying, questioning, and steering language-agent society simulations.
Devo Desktop Coding Agent
A model-neutral Rust coding agent runtime with a Desktop app and terminal TUI/CLI for private and intranet environments, connecting DeepSeek, Qwen, Kimi, GLM, or any compatible model endpoint.
My Free Code
A local multi-provider gateway for Claude Code and other coding agents: unified model routing, streaming, tool calls and ordered fallbacks behind one API endpoint.
LLM-in-Sandbox
Put your LLM inside a Docker-isolated code sandbox and it beats the standalone model on math, physics, chemistry, long-context and instruction-following tasks — no extra training required, and RL amplifies the gains further.
VectorVein
No-code AI workflow software: drag and drop nodes to build automated workflows powered by LLMs and your personal knowledge base.
Marvin – A Python Framework for AI Workflows
Type-safe structured outputs and orchestratable multi-agent tasks for building reliable AI workflows.
OptiLLM Inference Optimizer
A zero-training OpenAI-compatible proxy that boosts reasoning accuracy by 2-10x using 20+ inference optimization techniques.
3code Economical Coding Agent
Treats your token budget as a first-class constraint — 5× the work per token so subscriptions last and free tiers work.
Functionary: Conversational LLM for Controlled Tool Use
Functionary is a language model that can interpret and execute functions/plugins, deciding when to call tools and understanding their results.
VCP ToolBox
A self-hosted layer that connects model APIs to persistent memory, distributed plugins, and a unified command protocol.