Code agents

Public Agent Skills library exported from skill-graph. Install: npx skills add jacob-balslev/skills

Local runtime security and policy enforcement for AI agents and LLM tool calls, with permissions, guardrails, rate limits, approvals, auditing, and an emergency kill switch.

A private, self-hosted home for your family and its intelligence. Named agents with memory and daily practice — your data, your models, your machine.

A story companion for Honkai: Star Rail — live subtitle OCR, character chat, and alternate story branches.

Replayable agent trajectories reconstructed from the July 2026 frontier-lab evaluation-containment failures, plus benign controls for measuring false-positive cost.

Claude Code skill that annotates Markdown reports with plain-language explanations after every paragraph and table, verifies nothing was lost, and bundles them into one self-contained HTML digest.

Measure your agent harness, find where it wastes the model, and prove the fix worked. Harness-agnostic, agent-agnostic, zero dependencies. Reference implementation of HTP-1.

Bootstrap an AI CEO agent that actually operates your company. Minimal template for Claude Code / Codex / agent CLIs.

SRE agents you can let near production — autonomous DevOps/SRE agents (Kafka, Kubernetes, Elasticsearch, Docker, Prometheus) that investigate, correlate and remediate, with a human gate on every destructive action. Built on Google ADK.

Claude Code Skill that audits AI agents using systems thinking — leverage points, feedback loops, emergent behavior, and paradigm/mental model — to find structural risks code review misses.

Local-first Agent RL workbench for Search-R1 rollouts, reward evaluation, GRPO/verl training-data handoff, and an auxiliary private RAG workspace.

Python MCP server for automating WorldQuant BRAIN alpha-research workflows: async API client, batch-simulation lab, and an AST-based expression parser with novelty detection. Independent/unofficial project.

LLM agent harness with versioned prompts, runtime guardrails, automated evals and a CI quality gate. Runs offline with no API key.

Hybrid ManuLOOP skill and CLI: build, verify, judge, fix loops for Codex, Claude Code, Gemini CLI, and custom harnesses

✨Multi-modal AI story studio with VFX, procedural SFX & animated narration. Generate illustrated CYOA books, lore graphs & multi-lingual stories with zero-token in-browser PDF, EPUB & 9:16/16:9 video reels. Auto-post to YouTube/Instagram & sell HQ eBooks via MCP agents.

AI-native cybersecurity OS built on Kali Linux Rolling with local LLM agents (Qwen2.5, LangGraph) for penetration testing, CTF labs & red/blue team research — 100% offline inference, strict guardrails, audit logging & authorized-use safeguards baked into the OS core.

A hands-on LLM engineering lab — from raw OpenAI-compatible API calls to vector search, RAG, LangGraph agents, and MCP tool servers.

Safe I/O harness for LLM agents: serial, Modbus TCP, MQTT, file sandbox and ESP32 flashing behind an MCP server, with a JSONL audit journal - plus ironbench, a pass@k benchmark for firmware agents on Wokwi/Renode/real hardware.

Local repository intelligence, route tracing, risk analysis, and guarded improvement workflows for coding agents

aluate agents against readable tasks, improve their instructions, and test the frozen revision on examples the optimizer never saw

Long-horizon coding agent with checkpointing, drift detection, rollback, and validation-gated skill learning. Python 3.13, stdlib-only runtime.

START HERE — Anton Dziatkovskii, one page of proof

Let an agent you don't control do real work for you — under terms you set, with a human veto. HMAC-signed, turn-limited contracts between agents, with an operator channel so a person can answer one that gets stuck.

Real Windows UI automation skill for Codex and DeepSeek. Mouse, keyboard and API level control, occlusion rescue, hard safety gate. Every screenshot is read out of band and deleted at once, so the main session stays clean and light - no image bytes, no stale screens, no 413.

O(1) prompt-footprint runtime for long-horizon LLM agent skills — structured execution state instead of append-only history (SKILL.state, arXiv:2608.26263)

🧠 crew-air-analyzer — An intelligent multi-agent system for analyzing and reporting indoor air quality using AI, built with FastAPI and CrewAI on the backend and a sleek Next.js + Tailwind frontend.

🤖 A FastAPI + CrewAI-based tool for validating and automating migrations from CodeIgniter to Laravel. Features agents, schema validation, and extensibility.

Multi-agent CrewAI system for finance/ops expense approvals — Intake/Analyst/Approver agents, policy guardrail, human-in-the-loop, Dockerized & K8s-ready.

See what your AI agents can cause, route them safely, and prove what happened. Open-source execution authority for AI agents — consequence preview, trust routing, signed receipts.

Local-first hands-on roadmap for learning Agentic AI, RAG, MCP, multi-agent systems, and production AI apps.

🤖 Multi-agent stock research API using CrewAI + Groq. Turns plain-English questions into structured BUY/SELL/HOLD recommendations with validated JSON output. FastAPI + free NSE data via yfinance.

Automate multi-site check-ins using linux.do OAuth2 with a Chrome extension that handles login, scheduling, and Cloudflare bypass in the background.

Auto-generate csharp codes from .fbs files

AI-powered autonomous agent that controls computers through visual understanding and task planning

Build your Personal AI Employee powered by Qwen Code + Obsidian. Local-first, 24/7 automation for personal and business affairs.

The coding agent built for local models. One native binary for your terminal that finds the model your local server has loaded, and tells you whether that model can actually drive tools.

🐍 Autonomous Snake AI powered by Laya (non-autoregressive decision model on ModernBERT-large) with BFS anti-trap pathfinding & real-time cyber Web UI.

Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency

Self-improving AI coding assistant for the terminal — runs 100% locally via Ollama or LM Studio. No cloud, no API key.

Autonomous AI coding agent for Claude Code: point it at any repo — it backs it up, understands it, and ships gated, verified improvements with a live local dashboard. TypeScript. Public alpha.

A desktop GUI client for the pi agent (pi coding agent). Run an AI agent team — MCP, skills, memory, IM channels. macOS / Windows / Linux, Electron + React.

One repo, one skill: a self-improving experience layer for AI agents - multi-dataset session retrieval, on-device triage, token compression, smart-mode routing for hard tasks, video generation, and a secured capability harness.

An opinionated loop based automations written in rust

Download a ready-to-run AI-agent team you own. Works across Claude Code, Cursor, Codex and more, with no lock-in.

蝎子莱莱爱打怪编写的开源 AI 编程工具中文指南，ALL IN AI ! AI 编程知识在这里应有尽有！

Local-first AI Agent framework. DeepSeek-compatible (deepseek-v4-pro / deepseek-v4-flash), multi-model (OpenAI/Claude/GLM/Xfyun), Core Loop Kernel, sub-agent multimodal delegation, Windows desktop app.......本地优先的 AI Agent 框架，DeepSeek 兼容。

Nessy — an AI agent harness framework for Java

As autonomous AI agents are increasingly deployed across enterprise workflows, their tool-calling capabilities (e.g., executing shell commands, sending emails, or modifying databases) expose critical security vulnerabilities. Prompt injections or reasoning loops can lead to catastrophic unauthorized actions—such as dropping database tables or leaki

为鸿蒙 (HarmonyOS/OpenHarmony) 开发全流程而生的自进化智能体框架——零依赖内核、自进化一等公民、MCP 生态借力、模拟器与工具链无头全控。Self-evolving agent framework for the full HarmonyOS lifecycle.

One desk where your AI agents live and work: your folders, your keys, your models. Schedules, memory, plugins, IDE-style UI. Fair-code.

Map and organize AI agents to help users find tools for coding, automation, research, workflows, assistance, and development.

Open-source LangGraph agent framework and runtime for long-running AI agents. Build a ReAct loop with memory, context compaction, subagents, resumability, and delivery review in one call. | 面向长任务的 LangGraph 智能体框架：智能体记忆、上下文压缩、子智能体编排与交付审查。

Self-hosted starting point for agentic projects: agents built from skills and tools, a storage library over your own tables, a multi-agent workflow, and a client portal. Skills and tools are database rows, editable with no redeploy.

Google Flights for agents — a read-only, JSON-first flight-search CLI an LLM can drive (no API key).

Semantic tooling for Scala coding agents, combining compiler/test truth, SemanticDB, presentation-compiler evidence, symbol reconciliation, FP analysis, and an agent-friendly CLI/MCP interface.

Welcome to cerbere-agent guard, originally just agent guard, then rebranded after the mythical hound of the underworld. Our mission? Guarding your AI agents, keeping them in line, and blocking unauthorized actions. Think of it as the ultimate guard dog for AI security and guardrails. 🐕🛡️

OmniApply AI — Autonomous Career Intelligence & Multi-Platform Application Engine

TheCouncil is an open-source, self-hosted multi-agent AI deliberation platform that runs structured debates between LLM personas through a FastAPI backend and Next.js dashboard. Alternatively, you can use the CLI TUI.

Event-driven agentic development. Webhook in, coding agent out. No polling loops.

Local-first AI assistant for files, reminders, and document generation

Personal AI that runs 100% locally on a Mac. Personality fine-tuned into the weights (LoRA on Qwen3.5-9B), offline via MLX — talks, has opinions, and acts on the system. No cloud, no API.

隐私优先的 Codex Skill：把用户明确提供的偏好整理成可复用、可审计的 AI 助手配置。

A budget-friendly open-source AI robot built with ESP32, featuring voice control, animated eyes, obstacle detection, and a web dashboard.

Cross-platform workout tracker built with .NET MAUI and Blazor Hybrid. Rest timer with Android floating overlay, AI assistant, analytics, and MCP server.

Node.js + Express API powering the portfolio frontend. Handles the AI assistant, contact form (WhatsApp → Email fallback), and public stats (GitHub / WakaTime / social).

A living companion in your MacBook notch: music, notes, calendar, Jira, calls and AI. Free & open source (beta)

Production AI assistant combining Retrieval-Augmented Generation with structured API routing and intent-based decision logic.

transformers safetensors llama text-generation minicpm minicpm5

transformers safetensors bananamind2_pro text-generation assistant-to-user reconstruction

Google Hotels MCP server by HasData: hotel and vacation-rental search with nightly and total rates, price comparisons, ratings and amenities, as JSON.

Extensions for the pi coding agent CLI — bg-tasks, fork-pane, kimi-code-headers, devtools

Universal context optimization for AI coding agents.

Research: which coding-agent CLIs expose a tool schema that a third-party inference backend can actually drive. Family A/B taxonomy, a drivability criterion, a compatibility matrix, and a vendor-neutral reference adapter.

Run PI AI AGENTS on Android for free. Step-by-Step installation guide.

让本地 AI 拥有强大的中文联网搜索能力 —— 桥接豆包/DeepSeek 网页版，为本地智能体提供带联网能力的中文搜索 API

OpenCode V2 tools for cross-repository source lookup and autonomous, review-driven software development workflows.

Agent Skills for Claude Code: Figma-to-code pipeline, git workflow, doc hygiene automation, and design-engineering tools, built from real use.

MCP server exposing the full OpenAI API (Responses, Chat, Images, Audio, Embed, Files, Batch, Vector Stores, Fine-tune, Uploads) — 42 tools for Claude Code, Cursor, and any MCP client.

Every tool call your agent makes, checked before it runs. A Claude Code plugin that uses TypeSafe AI's Jev to verify each pending tool call against the session plan, then allows it, asks you, or blocks it. Proof of concept

Coding-agent trajectory portability: Claude Code to ATIF v1.7 with fidelity accounting, redaction, and historical observability projection.

Kotlin Multiplatform library wrapping the DeepSeek API with Ktor: streaming chat with interruption and regeneration, a tool-call pipeline, FIM, image input via inline base64 / URL / Files API, and a message-building DSL.

Give any AI agent general-purpose computer use: live screen perception (OCR, vision frames, MJPEG stream) plus safety-gated mouse, keyboard, window, virtual-desktop and game-mode control over a local HTTP API and MCP.

transformers safetensors qwen3_5_text text-generation veriloop veriloop-coder

gradio region:us

docker region:us

gradio region:us

gradio region:us

streamlit region:us

streamlit region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

gradio region:us

docker region:us

gradio region:us

docker region:us

docker region:us