Autonomous AI agents that perform tasks independently
skill-scoreboard contributors
Benchmark Claude Code skills against a no-skill baseline, detect token waste and skill bypass, and rank a whole skill library KEEP/FIX/MERGE/RETIRE.
...moreAr5en1c
MCP server that indexes code, logs and config locally and gives coding agents search tools over the index.
ybak
一本开源的 AgentScope Java 中文教程：7 篇 44 章、839 页成书体量的完整 Markdown 源稿，由浅入深覆盖从第一个 Agent 到生产级 Agent 平台的全部主题。
i4cobus
A conversational agent over a private corpus of 7,655 Chinese web novels (plain TXT, ~36 GB). LLM-built book cards and a Qwen3 multi-vector index turn the raw text into searchable artefacts; the agent searches, verifies constraints per book, recommends with reasons and answers in-book questions. Two-stage evaluation: index supply, agent protocol.
...morebryan-cmf
Temporary package placeholder for staged publishing
Agentic coding CLI for local models (Ollama, vLLM, llama.cpp), Anthropic, OpenAI, Bedrock, and Triton
blockpay-dev
Agent wallet for BlockPay: budgets, approvals, audit trail, LLM tool adapter.
GitHub Actions
Run Chatwoot support from a Discord forum with humans and AI agents: a post per conversation, slash commands, AI drafts, and AI triage.
...moreMany Kasiriha
Agent harness for Robot Framework: an Agent Skill, agent hooks and a local robotcode-based live session for Claude Code, Codex, GitHub Copilot, VS Code and OpenCode.
...moreLangChain integration for TranscriptYT: YouTube transcript document loader and agent tools.
alexanderizh
SparkWork is a local-first desktop Agent workbench for professional development and complex work. Orchestrate workflows, collaborate across Agent sessions, route tasks to the right models, and extend the workspace with custom tools and apps. Reviewable, steerable, reversible runs on macOS, Windows and Linux.
...moreBkashJEE
Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, routines, gateway.
...morekuafuai
An agent that moves into your Android phone and becomes its soul — not an assistant, not a tool. Any app, no integrations, on-device, one APK.
...morebadhope
Spark — local-first coding agent (Python + React), self-hosted, MCP-native, with tool sandbox, repo-map context and OTel observability. 本地自托管的 AI 编程智能体。
...morejunxchan54-maker
把麦当劳中国 MCP 的 36 个工具编排成「活动推送 + 关键词关注 + 最优惠点餐+多人群点聚合」算价走真实计算、下单必须二次确认，帮你不错过活动也不多花一分钱。The 36 tools of McDonald's China MCP have been organized into three business flows: "event push + keyword Follow + Best Offer Ordering". The pricing is based on real calculation, and orders must be confirmed a second time. This helps you not miss any events。
...moreagimx-ai
An extensible desktop AI workspace that connects models and agents to local files, applications, and system tools through secure, installable plugins.
...morepatriceckhart
Yet another coding agent harness, lightweight and written in go.
erwinmsmith
An agent-native development node framework for on-demand scaling and low-cost evolution of agent structures.
MaxonT
Curated, star-ranked catalog of AI agent frameworks, coding-agent harnesses and workflow platforms (EN/中文), auto-refreshed.
...morecmcoffee
Your agent has agents. A self-hosted, local-first AI agent platform in one Go binary: agents hand work to specialists and build the tools, agents and apps they lack, with sandboxed tools and credentials the model never sees.
...moreYuji Arima
Agentic ETL for Python: YAML pipelines where each step is a connector, a function or an LLM agent.
Thanatchon Chongmankhong
Operationalise the MAS Guidelines on AI Risk Management (2026) for LLM and agentic AI systems: inventory, materiality, controls, evidence and audit packs.
...morePack a repository into a single, LLM-friendly Markdown file.
lupuletic
The THG Hyper-Personalisation event specification: versioned JSON Schemas, the event registry, a validator, generated TypeScript, Kotlin, Swift and Java event models, and the OpenAPI contracts for collection settings and the public API.
...more