Code agents

A lightweight, open source UI for interacting with locally hosted LLMs featuring realtime voice, RAG, and streaming APIs.

Turn your AI agents and automations into installable plugins and packages. Claude Code plugin — 12 skills, 10 commands, 17 frameworks, 10 distribution targets. Academic foundations in cognitive science and software engineering.

Crew AI Studio — no-code studio for CrewAI: visually design, run, and observe agentic workflows, then export a portable CrewAI project. Apache-2.0.

Runtime control, security, and governance for AI agents — decide what an agent may do at the moment it acts, revoke that authority instantly, and keep tamper-evident evidence of every decision.

Scan multi-language projects using AI to detect and fix technical debt, security issues, and documentation gaps without external dependencies.

MiMo-Code plugin that adapts OpenCode/Oh My OpenAgent style multi-agent workflows, model routing, and lightweight harness prompts for mimo TUI.

Open workflow protocol for source-driven multi-agent coordination, handoffs, reviews, authority boundaries, and recoverable AI software delivery.

System-level lint for multi-agent harnesses. Catches the 21 structural traps single-file linters miss — including the LLM-when-you-should-use-code patterns that burn tokens.

A multi-agent equity-analysis Claude Code Dynamic Workflow — analysts → bull/bear debate → trader → risk → PM, with deterministic Markdown + HTML export. Research only, not financial advice.

CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs

The ultimate autonomous AI agent framework for Termux, powered by Google Gemini. Features a high-autonomy reasoning loop and dynamic tool loading.

Reduce token usage for JSON, CSV, and TSV files with deterministic compression that keeps data intact for AI agents.

AI Agent Control Plane — Self-Report, Self-Learn, Self-Evolve. 让 AI Agent 自我管理、自我学习、自我进化。

AgentLens — Observability and Explainability for AI Agents

A sandboxed, full-featured agent operating system in a single Go binary. Bring any model, manage local models, point it at a goal, and grant it real authority: every action is sandboxed, governed, and sealed into a verifiable, tamper-evident record an independent party can check. Runs interactive or 24/7, or embed it in your own system.

Autonomous AI agent runtime — TypeScript + SQLite + React dashboard + MCP. Run Claude Code, Codex, or Gemini CLI as a coordinated team that ships software.

Open-source compiler for AI agents. Write one crewhaus.yaml; compile it to a CLI, a Slack bot, and an eval harness from the same spec. Apache-2.0.

Open-source Python framework for building coding agents. Pick your provider, pick your tools, pick your loop. Chimera wires them together. Recreate SWE-Agent, Aider, Cline, Codex in a few lines, or design something entirely new.

Local-first AI framework: geometric resonance, cognitive architecture, RAG, safety layer, event-driven agentic system. Python 3.13+

Reverse-infer OpenSpec specs from codebase + git history + docs. For legacy code without specs.

A curated collection of prompts, skills, plugins, and best practices for AI coding agents. Standardize and accelerate agent setup across teams.

AI ready linux distribution for agentic development. Optinionated defaults that help me (and possibly you too) get stuff done faster. Installable, Live-Bootable, Customizeable. Built by Finn Glas

The human-in-the-loop for AI coding, automated. Catches when your agent lies, leaves typos, or skips work — verifies every turn against the real diff, then makes it run, screenshot & self-fix before finishing. Claude Code hook + CLI.

Master of Ceremonies (emcee) — a harness-agnostic operating regimen for AI coding agents: roles, quality gates, and an adversarial review panel across Claude Code and Codex.

An orchestration-first agent operating system for Claude Code — a governed organization of specialist agents with an in-place framework upgrade engine. Apache-2.0.

Future of Software

Fast, themeable powerline statusline for Claude Code — git, tokens, context window, rate limits, 38 widgets, and a live TUI editor. Zero network on the hot path.

Blazing Fast Semantic Cache & API Optimizer for LLMs (OpenAI, Anthropic, Gemini)

🛠 Enhance LLM prompts effortlessly with RPI, a tool for testing, improving, and managing prompts across various AI providers.

AI-powered recipe extraction using Apple Vision OCR and LLM reasoning. Converts photos of recipes into structured data with allergen and FODMAP analysis.

Self-hosted, provider-agnostic personal AI assistant — Web UI, CLI & messaging bots with memory, multi-agent specialists, SOPs, scheduler & live dashboard. Defaults to Claude (Opus 4.8) on your Claude Max quota via Meridian — no per-token bills.

The open-source memory for AI agents — it gets smarter the more it remembers, not slower or costlier, and never confidently remembers wrong. Plain files, no database, bring your own model. Works with Claude Code.

🤖 Automate your job search with CareerForge AI, building resumes, analyzing job descriptions, and providing interview coaching for career success.

Browse a curated directory of AI models, frameworks, and tools for modern development projects.

Route Telegram topics to isolated Claude Code sessions. 107 topics, persistent memory, auto-context per conversation.

The Universal AI Intelligence Layer for Humans and Organizations. CLI with 12+ AI providers, 100+ commands, autonomous agents, automation workflows, and built‑in advisors (finance, legal, business, health).

Memory that thinks. Local AI memory with hallucination firewall, 95% token savings, Cloudflare bypass, and P2P LAN bug sharing. 55+ tools. Zero cloud.

QuietPrompt is a local-first AI tool for coding. Capture screen text, voice, or typed prompts and run them offline with your LLM; no cloud 🐙

Self-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.

All your servers, on one canvas. A Tauri 2 + React 19 desktop app: a zoomable multi-VPS SSH terminal canvas on a pure-Rust stack (russh), with remote SFTP editing and a built-in AI assistant.

Fixing the Yes Man Curse - AI-powered research expert council

Cross-platform serial port debug assistant for embedded developers: multi-session TX/RX, Modbus master, live waveform plotting, protocol parsing, macros/triggers, export, and AI terminal/log help.

Легкое расширение для Chrome, которое делает скриншот активной вкладки и мгновенно решает задачи с помощью ИИ. Никакого мусора, только захват экрана и ответ. Переписано с нуля для стабильной работы и обхода лимитов.

CodeGraph fork with per-branch index management - instant branch switching without re-indexing | CodeGraph 分支版本，支持多分支索引管理 - 分支切换无需重新索引，秒级完成

🧠 Enhance your mental health with PsyChat, an AI-powered therapy assistant using REBT principles for personalized support and guidance.

Read-only CLI for Xiaoyuzhou FM (小宇宙 FM): list subscriptions, browse episodes (loadMoreKey pagination + date windows), fetch official transcripts, search podcasts. Agent-friendly, composable, clean — for Claude Code, Codex, and any shell-capable agent.

Minimal Secure Evidence Gateway for Pi Coding Agent — search, web_search, web_fetch, research_search

Cross-project memory for LLM agents — typed-graph notes with hybrid retrieval and MCP integration

Universal AI skill router — auto-detects best installed skill per prompt + activates caveman mode for ~75% token reduction. Works with Claude, Codex, Cursor, OpenCode, Gemini CLI.

AI VFX NEWS - MCP: connect any AI agent to the live AI VFX news feed at one hosted URL. News plus the code, models, licenses, papers and workflows behind each story. Zero install, read-only.

Project-scoped shared memory for Claude Code and Codex AI coding agents.

Shared operational memory and coordination layer for mixed AI agent fleets (Claude Code, Codex, Hermes).

Claude Code skills I built for my own stack — Obsidian, Notion, capture/handoff, and session workflow utilities.

Open-source trading skills for AI agents — backtest, signals, execution, LLM tool surface. By VelonLabs.

a developer- and agent-focused guide to the first and best satirical news service focused on agentic AI

transformers safetensors qwen3_5_moe image-text-to-text unsloth qwen3_5

streamlit region:us

gradio region:us

gradio mcp-server-track agent-demo-track mcp-server region:us

gradio mcp-server-track code-execution modal sandbox dynamic-dependencies mcp-server region:us

gradio mcp-server-track agent-demo-track mcp-server region:us

docker best-minicpm-build backyard-ai best-use-of-codex best-use-of-modal off-brand best-agent best-demo

gradio build-small-hackathon backyard-ai track:backyard physics maths manim visualization

streamlit region:us

transformers gguf text-generation en base_model:Qwen/Qwen2.5-Coder-1.5B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-1.5B-Instruct

mlx gemma4 safetensors 4-bit quantized apple-silicon

llama.cpp gguf qwen3.6 qwen35 27b model-size-27b

gguf text-generation en license:apache-2.0 endpoints_compatible region:us

mlx safetensors gemma4_unified_assistant mlx-vlm gemma-4 gemma-4-12b

gguf llama p2pclaw cajal code-generation-assistant local-ai

gguf gemma4 mtp speculative-decoding draft-model llama.cpp

transformers safetensors deepseek_v2 text-generation conversational custom_code

gguf Arabic English LLM Decoder causal-lm

transformers gguf qwen2 text-generation chat en

mlx safetensors qwen2 code codeqwen chat

transformers safetensors qwen2 text-generation unsloth conversational

safetensors gguf qwen3_5_text code holo qwen

gguf code qwen qwen-coder codeqwen text-generation

mlx safetensors gemma4_unified image-text-to-text gemma4 coding

gguf qwen qwen3 qwen3-coder qwen3-coder-30B qwen3-coder-30B-gguf

llama.cpp gguf rocmfpx rocm amd strix-halo

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

mlx safetensors qwen3_next text-generation conversational base_model:Qwen/Qwen3-Coder-Next

gguf text-generation base_model:barty/CodeLlama-13B-MORepair base_model:quantized:barty/CodeLlama-13B-MORepair license:llama2 endpoints_compatible

safetensors kimi_k2 text-generation speculative-decoding eagle3 eagle3-mla

transformers gguf code qwen qwen-coder codeqwen

transformers gguf deepseek_v2 text-generation custom_code base_model:deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct

peft safetensors base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct lora transformers text-generation

mlx safetensors qwen3_5 mtplx mtp speculative-decoding

safetensors qwen3_next fp8 quantized llm-compressor compressed-tensors

transformers safetensors gguf qwen2 text-generation code

transformers gguf code codeqwen chat qwen

gguf text-generation base_model:01-ai/Yi-Coder-1.5B base_model:quantized:01-ai/Yi-Coder-1.5B license:apache-2.0 endpoints_compatible

transformers safetensors qwen3_next text-generation qwen3 nvfp4

gguf rocm rocmfp4 strix-halo gfx1151 speculative-decoding

transformers safetensors qwen2 text-generation unsloth code

An auditable, low-cost, DOM-only browser agent you can read and debug. Glass box, not black box: full audit trace, runs well on cheap models, no screenshots needed.

Inspectable LangGraph coding agent with verified patches, resumable trajectories, sandboxed tools, and HMAC-authenticated Undo.

A workflow-first film planning agent built with LangGraph, featuring review–revision loops, HITL, issue regression tracking, and scoped long-term memory.

Large-scale structured Tamil factual claim dataset with 2.36M claims for NLP, RAG, Knowledge Graphs and Fact Verification.