Autonomous AI agents that perform tasks independently
SecureVector
SecureVector SDK for CrewAI — brings the local threat monitor's three controls (tool-call permissions, secret/data-leak detection, threat detection) to every CrewAI tool call, with tamper-evident audit logging.
...morezhenfengxx
Authenticated API client and signing helpers for AutoDevOps BuildAgents.
Perseus Computing LLC
The billing layer for AI agents — self-hosted, Stripe-integrated usage metering and prepaid-credit billing for LLM/agent spend.
...moreA lightweight, zero-dependency, provider-agnostic LLM agent with tool-calling support for Anthropic, OpenAI, Gemini, and Ollama.
...moreosama96gh
Educational Python coding agent built from scratch to explain agent loops, tool calling, code editing, bash execution, permissions, context management, and OpenAI/Gemini providers.
...morealexverify
Trust and verification for the skills your AI agent installs.
GitHub Actions
A local-first AI secretary that gathers your scattered work context into private memory you and your AI agents can query over MCP. It advises you, and proposes replies, tasks, and decisions, with nothing sent or saved without your approval.
...moreverlox
Governance SDK for autonomous AI agents: audit trails, policy enforcement, kill switch, and compliance. Connects any agent stack to Labyrinth Scout.
...moreGitHub Actions
Governed configuration, Sentinel-rule, and feature-flag operations CLI for AI agents (Nacos, Apollo, etcd, Kubernetes, Consul)
...moreagent-scaffold contributors
Generate runnable AI agent projects from markdown specs in the agent-deployments repo.
iOS Test Generator Team
AI-powered iOS test case generator supporting OpenAI, Anthropic, Groq, and GitHub Copilot
Minwoo Kim
Bring-your-own-LLM context curation: memory with provenance, implied-intent inference, multilingual deep research — any model, even small local ones, acts smarter.
...moreMTSP-Solver Team
RCH: Partial-Expansion Anytime Focal Search solver for heterogeneous multi-agent TSP
LangChain tools for Hlido — vet an AI agent against its independent, evidence-backed trust score before delegating to it.
...moreGao Yuwei (Willsgao)
Lightweight zero-dependency Agent orchestration framework: Tool Registry, Pipeline/ReAct Agent, Multi-Agent Orchestrator, Pluggable Verification, and Loop Engineering
...moreSachin7456
Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your machine.
...moremoyunzero
Terminal-native AI coding agent with Plan/Build modes. Bun + OpenTUI TUI, local tool execution, multi-LLM support.
avacadorun-dev
Proactive CLI coding agent with self-modifying skills, context management, and hybrid visual tooling.
Yht20927
基于 Bridge Framework 的抖音全自动评论管理工具。搜索视频、爬取全量评论（含嵌套回复）、AI 智能回复、运营仪表盘。
cengicadis
Evidence-backed validation framework for AI agents, Cursor skills, MCP orchestrations, and agentic repos. Structured rule catalog, verified evidence standard, and certification output. Free, open-source, MIT.
...morecaihongfairys
Forging a minimalist universal language for AI, unconditionally eradicating hallucinations and automating Agent Swarm intelligence.
...moreIkarusMK
Self-hosted MCP server that turns your NAS into a persistent brain for Claude (or any LLM): memory, skills, tools, MQTT/FTP devices & an encrypted vault — desktop + mobile, secrets stay home.
...moreGitHub Actions
Cloud human input handoff for AI agents.
yohanesvito
MBG (Mantle Bot Gate) Skill — TEE-attested on-chain risk scoring for Mantle DeFi. Installable as an OpenClaw / Byreal Skill so AI trading agents can pre-check Mantle protocol and route risk before signing, and surface a verifiable attestation hash to thei
...more