Autonomous AI agents that perform tasks independently
Carry an AlgoVoi keystone decision into a crewAI run: a recomputable execution_ref under algovoi.keystone.*, verifiable offline
...moreemiliaprotocol
Guard LangChain.js tools with EMILIA Protocol — require an offline-verifiable authorization receipt (EP-RECEIPT-v1) before an irreversible tool runs: missing -> refused, valid -> runs, replay -> refused, forged -> refused (RR-1). The approval becomes port
...moresdougbrown
Agent profiles for pi — preconfigured model, system prompt, tool restrictions, and permission gates
hameragentt
The Autonomous Intelligence Layer — Build, deploy, and scale autonomous agents with memory, reasoning, workflows, and multi-agent collaboration.
...moreGuard CrewAI tools with EMILIA Protocol — require an offline-verifiable authorization receipt (EP-RECEIPT-v1) before an irreversible tool runs: missing -> refused, valid -> runs, replay -> refused, forged -> refused (RR-1).
...moreJeff Steinbok
Agent Eye dashboard for monitoring GitHub Copilot CLI sessions in real-time
Aarav Khanal
The persistent memory layer for AI coding agents
An integration package connecting Verifly (agent-native email verification) and LangChain
claimgate contributors
CI for AI-agent quality — a regression-testing harness for AI agents.
Zhao Yu
A multi-agent system for scholarly research and information retrieval.
LING71671
Open-source reverse engineering lab: 197-article knowledge base + MCP tools + CTF/APK/PE automation toolchain. Agent-native.
...morelioensky
VCP 部署在 AI 模型 API 与前端应用之间，是面向AGI OS开发和探索的工业级基建示范项目。通过统一指令协议、多层级持久化记忆、分布式插件引擎及多 Agent 协作框架，将原本“无状态、无记忆、无工具调用能力”的大语言模型，彻底改造成拥有永久自我意识、物理世界操作权及群体协作智能的完整智能体系统。
...moreMorgan-C-CV
A high-performance, developer-centric agentic runtime built in Rust.
LiuZhen515
《智能体工程：从一句话到一个闭环》（Prompt · Context · Harness · Loop），本书将大语言模型驱动的智能体系统拆解为四种递进的工程范式，四种范式从 Token 到 System，从一次调用到完整的自主闭环，构成了智能体系统的完整工程视图。
...moreServe any LangGraph graph over the OpenAI Chat Completions + Responses APIs.
OpenGuardrails
Guard a Hermes agent and its sandbox through the OpenGuardrails (OGR) protocol — one policy enforced across the LLM gateway, the agent tool-call hook, and the real sandbox exec.
...moreForge — an open-source, enterprise-ready multi-agent orchestration platform with cost awareness, governance, and security built in.
...moreLangGraph abstractions for hierarchical multi-agent systems
jace_jia
De-duplicate and centralize agent skills across directories
iwedmak
Reserved namespace alias for `@ceki/langchain-ceki` — install that for the real package.
vickyrathee
Ticketdesk chat for live human customer support + AI chatbot using ChatGPT 5. Provide instant automated responses, AI-powered self-service, and assign to human chat support agents for better customer experience.
...morerutvik308
Unified natural-language search and resume for coding agent sessions
rutvik308
Unified natural-language search and resume for coding agent sessions
maitham88
UR terminal coding agent CLI