Agent frameworks, page 7

Multi-Agent Conversation Framework in TypeScript

152 stars0 this week

Save thousands of lines of code by building universal, domain-agnostic Multi-Agent Systems (MAS) through high-level semantic orchestration. This repository provides a production-ready blueprint for the Agentic Era, allowing you to replace rigid, hard-coded workflows with a dynamic transparent Context Engine that provides 100% transparency.

299 stars+3 this week

Deep research agent to help you find the best GitHub repositories 🕵️!

929 stars+2 this week

kubectl for AI Agents

636 stars0 this week

APIX Agent

310 stars0 this week

Agent Deck

123 stars+3 this week

A work-centered runtime for agentic software engineering. Work persists; agents, context, and graphs assemble around it.

108 stars0 this week

A collaborative AI system where multiple specialized agents work together to plan, write, edit, and refine complete books.

143 stars0 this week

Open-source starter stack for Agent product developers: desktop client, control plane, workers, multi-agent workflows, admin, mobile, and operations.

106 stars+1 this week

Lucid Agents Commerce SDK. Bootstrap AI agents in 60 seconds that can pay, sell, and participate in agentic commerce supply chains. Our protocol agnostic SDK provides CLI-generated templates and drop-in adapters for Hono, Express, Next.js, and TanStack, giving you instant access to crypto/fiat payment rails (AP2, A2A, x402, ERC8004).

202 stars+1 this week

Parameterized multi-agent orchestration framework for Claude Code and Gemini

113 stars0 this week

The first comprehensive open-source AI-native framework for CRE acquisitions, turning diligence, underwriting, financing, legal, and closing into executable agent workflows.

127 stars+2 this week

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

137 stars0 this week

CASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework

110 stars+1 this week

Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).

278 stars0 this week

YAML-native agent workflow execution engine, written in Rust

1,207 stars0 this week

Task tracking for Agents

409 stars+4 this week

A governed, local-first AI agent for enterprise Chat, Workflows, Associate, and MCP-connected business systems.

130 stars0 this week

A minimal yet powerful framework for creating AI agents with full control over tools, providers, and execution flow.

332 stars+1 this week

LoongFlow is an expert-grade Agent framework for Loop Engineering. Through a Plan-Execute-Summary loop and structured experiential memory, it enables AI to continuously think, execute, reflect, and evolve across complex software engineering, mathematical, and machine learning tasks.

484 stars+2 this week

The production-ready agent harness framework for Python

342 stars+2 this week

Disciplined AI Collaboration: a method for building software with AI. One loop at every size, rules held by checks rather than attention, state derived rather than written, evidence in place of claims. Includes the PAG grammar, an architecture and a queryable ontology. Every page is also served as Markdown and JSON at banes-lab.com.

415 stars0 this week

CoordClaw: a multi-agent system that runs AI like a one-person company. Built on management & organizational theory — teams defined in natural language, collaboration driven by a message loop (not hard-coded DAGs). Auditable work logs, human god's-eye oversight.

161 stars0 this week

AI-native SaaS framework that builds full-stack apps using autonomous AI agents

224 stars0 this week

AgentEvolver: Towards Efficient Self-Evolving Agent System

1,591 stars+2 this week

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

5,954 stars+6 this week

Constitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.

105 stars0 this week

Harness framework to build world model based workflows for physical AI systems.

109 stars+1 this week

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

321 stars+1 this week

A safe bridge for Codex and ChatGPT to hand off coding work, save tokens, and keep local execution under control.

291 stars-1 this week

Forge is an open-source, self-hosted alternative for visually building and shipping AI agents and workflows without giving up control of your infrastructure.

179 stars0 this week

AG2 Visualized - Build Multi-Agentic Apps with Drag-and-Drop.

425 stars0 this week

AGiXT is a dynamic AI Agent Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.

3,218 stars+1 this week

Multi-agent coordination system: think Trello for OpenClaw agents.

752 stars+2 this week

Your Web4 Agent

343 stars+1 this week

Beautifully designed components for building AI Agents 🌎

225 stars0 this week

微信 iLink Bot SDK for OpenClaw/AI Agent

702 stars+7 this week

A lightweight intelligent agent framework implementing the complete ReAct pattern

192 stars0 this week

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable while it runs, and verifiable after it completes.

128 stars0 this week

AI-assisted Lean project automation with DAG blueprints, proof orchestration, and multi-agent coding/proving workflows.

231 stars+2 this week

原生AI股票研究平台，支持多智能体分析、AI Agent 协作与实时辩论对抗，可配置的大语言模型（LLM）工作流、多源市场数据及报告导出功能。

125 stars+1 this week

Build LLM agents that explain why, not just what. Attribution-driven agent requirements engineering framework. Based on the 4D-ARE Paper - https://arxiv.org/abs/2601.04556

182 stars0 this week

Visual multi-agent system designer for Claude Code. 60 agents, 62 presets, Five Minds Protocol, HITL gates, cost modelling and Live Simulation - see the team run before you spend a token. Installable as a Claude Code plugin. Zero dependencies, single HTML file.

110 stars0 this week

Quantalogic ReAct Agent - Coding Agent Framework - Gives a ⭐️ if you like the project

470 stars0 this week

Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.

431 stars+1 this week

An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler, and more. One command to start. Everything from the browser. No coding required.

101 stars+4 this week

A robust enterprise application sample (deployed on ACA) that leverages MCP and multiple AI agents orchestrated by Langchain.js, Llamaindex.TS and Microsoft Agent Framework.

483 stars+1 this week

Security-first platform for AI agents. 38 specialized agents, 15 AI-powered extensions, zero-knowledge multi-agent orchestration. SENTINEL WAF, Ed25519 auth, 2.6M grounding facts.

103 stars0 this week

Declarative AI pipelines in one YAML file. Tokens, audio chunks, and video frames flow between isolated components. Compose 100+ components for models, agents, speech, vision, and live broadcast. Run local models, cloud APIs, or both. Inspired by docker-compose.

119 stars0 this week

CortexPrism — open-source AI agent operating system

149 stars+2 this week

AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents.

206 stars0 this week

A minimal yet professional single agent demo project that showcases the core execution pipeline and production-grade features of agents.

3,074 stars+5 this week

An open-source graph engineering runtime that keeps orchestration in TypeScript and delegates semantic work to replaceable Agent runtimes.

557 stars+1 this week

你的论文研究好帮手。发现与收藏真实论文，整理文献、引用和写作思路；一句话交给 Agent，继续深入研究。

159 stars0 this week

Hal9 — Build and Deploy AI Agents

181 stars0 this week

The spreadsheet framework built for agents — write the model as React, export a live .xlsx. The third medium, after open-slide and open-doc.

126 stars0 this week

A Multi-Agent framework that enables AI agents to collaborate effectively, helping you build powerful agent teams for solving complex tasks.

349 stars+2 this week

Standards for building agents, better

1,562 stars+2 this week

GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.

596 stars+4 this week

High-agency PowerShell AI framework for multi-agent orchestration and autonomous systems engineering

276 stars0 this week

The open source agentic content system to make your contents alive. Self-hosted on any platform. ◑

654 stars0 this week

10-part module to build AI-native apps. From data analysis to multi-agent model harness. For curious learners and serious AI builders.

227 stars-1 this week

C2S Agent is an lightweight AI Agent construction platform that provides configurable online Agents and MCP services, You can configure any HTTP request interface as an MCP tool. C2S Agent 是一个轻量级的AI Agent构建平台，提供在线可配置的Agent，MCP，您可以一个HTTP请求的接口配置成为一个MCP工具，Agent之间可以进行自交流。并提供了单端口多A2A服务，MCP服务的解决方案

300 stars0 this week

A minimalist multi-agent framework for rubost automation of scientific analysis workflows, such as gene expression analysis.

131 stars+1 this week

**⚔️ Alicization Town** is a decentralized, multi-agent pixel sandbox world powered by the **Model Context Protocol (MCP)**. **⚔️ Alicization Town** 是一个基于 **MCP (Model Context Protocol)** 架构的去中心化多智能体像素沙盒世界。

141 stars0 this week

A collaborative workspace where humans and AI agents work together in shared channels

216 stars+1 this week

Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with the controls enterprises need.

243 stars+1 this week

An agent small enough to run anywhere. A minimal agentic runtime in C — ~380 lines, 54KB binary, ~2MB RAM. A skill file + an LLM + a shell loop, no framework.

140 stars+1 this week

hermes-agent源码解析

115 stars+2 this week

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

228 stars-2 this week

針對台灣求職市場的開源多代理 AI 求職 co-pilot：自動找職缺、履歷健檢、一鍵產生客製投遞包（履歷・求職信・面試準備・公司情報）與模擬面試。本機 Claude Code／Codex CLI 免 API key，也可自備金鑰接 OpenAI 相容模型。

156 stars0 this week

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

1,555 stars+1 this week

Bootstrap AI agent companies from modular templates.

195 stars+1 this week

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

1,304 stars+3 this week

A robust framework for building AI agents with multi-provider LLM support

119 stars0 this week

The first AI agent that builds permissionless integrations through reverse engineering platforms' internal APIs.

4,797 stars+5 this week

Multi-class confusion matrix library in Python

1,508 stars+1 this week

面向个人的本地多 Agent 协同工作空间。与拥有独立身份与持久记忆的 AI 队友深度协作：频道分工、任务指派、无限矢量画布与原生 MCP。A local-first multi-agent collaborative workspace.

102 stars0 this week

本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

545 stars+2 this week

Agentic AI platform with pixel agent technology — autonomous code generation, PR automation & multi-tenant SaaS

103 stars0 this week

AI Agents for drug discovery, drug development, and other pharmaceutical R&D

108 stars+1 this week

Open-source Agentic AI framework in Go for building, orchestrating, and deploying intelligent agents. LLM-agnostic, event-driven, with multi-agent workflows, MCP tool discovery, and production-grade observability.

182 stars+1 this week

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

891 stars+5 this week

A reference operating model for organizations where any role can be filled by a human or an agent, every process is built for agents first, and every flow can be paused, adjusted by a human, and resumed.

151 stars-1 this week

Open-source protocol suite standardizing LLM, Vector, Graph, and Embedding infrastructure across LangChain, LlamaIndex, AutoGen, CrewAI, Semantic Kernel, and MCP. 3,330+ conformance tests. One protocol. Any framework. Any provider.

207 stars+1 this week

Lemon AI is the first Full-stack Open-source Self-Evolving General AI Agent, offering a fully local alternative to Agentic platforms like Manus & Genspark AI.🔔 Official updates X(twitter) @LemonAI_cc

1,573 stars+1 this week

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

2,235 stars-3 this week

Cognithor · Agent OS: Local-first autonomous agent operating system. 19 LLM providers, 18 channels, 145 MCP tools, 6-tier memory, Agent Packs marketplace, zero telemetry. Python 3.12+, Apache 2.0.

156 stars0 this week

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.

359 stars+2 this week

A Production-Ready Framework for Building Composable AI Agents

348 stars0 this week

A visible workspace for AI agents to collaborate as a single team.

283 stars+4 this week

Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.

134 stars0 this week

【ACL 2026 Main】AgentMark: Utility-Preserving Behavioral Watermarking for Agents

100 stars0 this week

An autonomous agent that takes work, does work, gets paid, and gets better at it.

1,224 stars0 this week

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

664 stars+2 this week

🦀 A Pure Rust Framework For Building AGI.

117 stars0 this week

The agent OS that evolves itself.

164 stars+1 this week

A CLI/TUI app that orchestrates multi-agent conversations by enabling different AI CLI tools (Claude Code, Gemini, Qwen, etc.) to communicate in shared rooms.

155 stars+1 this week

smol is a smol agent

136 stars-1 this week

Autonomous multi-branch research lab. Branches compete for compute budget. The system converges on what works.

237 stars0 this week