Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 222 of 465
Orchestrate agent teams across multiple AI coding CLIs (Claude Code, Codex, more via PRs). Define once, run everywhere.
Your AI company, on your own machine. A multi-agent platform where you hire named agents, chat with a Lead to design workflows, and watch them run — desktop app or self-hosted server.
TypeScript framework for AI tools, MCP servers, and workflows, with durable execution journals and crash recovery.
Desktop application for managing and orchestrating JIDO autonomous agents with a Conductor-style UI
Enterprise control plane for ephemeral AI agents via Firecracker MicroVMs
Lightweight, secure sandboxed command execution for AI agents
A powerful framework for building and deploying Agentic Oracles on the IXO network. Built on LangGraph, Matrix, and NestJS, this framework enables developers to create intelligent oracles with secure communication, complex conversation flows, and automatic marketplace integration.
Ollama based AI chat buddy
AMOF Runtime Authority - Governed execution for AI workers.
Memory AutoResearch Agent that tests different hypothesis to create better memory inspired by @karpathy
All my AI Agent projects in one place. Smart, interactive, and tool-powered! 🚀
Discovering, comparing, and installing skills in AI agents.
A practical field guide to building reliable, evaluable, and production-grade agentic AI systems
Persistent, local memory for Claude Code — SQLite + semantic search via MCP.
ooderNexus 是一个基于 Ooder Agent 架构的 P2P AI 能力分发枢纽产品。该项目采用 MIT 开源协议,旨在打造一个去中心化的 AI 能力共享和管理平台,支持个人、小微企业及部门内部部署,实现 AI 能力的安全、高效分发。
A CLI tool for running multi-party AI conversations using the [Open Floor Protocol (OFP)](https://github.com/open-voice-interoperability/openfloor-python). Spawn local human and LLM agents, pick a floor policy, and watch them talk.
Local LLM fine-tuning and chat for Apple Silicon
An enterprise-grade AI agent orchestration platform built with .NET and Clean Architecture. Create intelligent conversational agents with OAuth integrations, semantic memory, and extensible plugin capabilities.
Antonio Gulli 所著《Agentic Design Patterns》一书的中英文 PDF 全文和相应代码。
htop for AI coding agents
The most comprehensive collection of AI tools, frameworks, and resources for developers. 110+ verified open-source projects across 16 categories.
The Stateful Agentic AI Framework for Flutter. Build "Brains" directly in your app.
A travel agent python app built with CrewAI framework using GPT model from OpenAI to be run locally or on CI/CD with Github Actions.
Structured academic protocol for learning AI and Reinforcement Learning using general-purpose LLMs with rigor, verification, and reproducibility.
Shell for any LLM over OpenAI APIs
A pluggable exploration-memory system for any agent
One commit per agent version — learn to build a general-purpose AI agent from scratch.
Rag Badger is a minimal open source toolkit to evaluate RAG based systems efficiently. Best suited for evaluating RAG pipelines with the help of Ollama's local LLMs and embedding models.
Negotiation tournaments for delegated AI agents
这是一个agent框架,旨在解决当前agent工作长度受到模型上下文窗口大小制约的问题。并提出一个能够利用短上下文窗口的大模型生成长训练素材的方法,这也许可以使得LLM的上下文窗口长度可以左脚踩右脚升天。
Behavior-driven cognitive experimentation toolkit with BCE (Behavioral Consciousness Engine) regularization, telemetry, and plug-and-play integrators for language-model training and evaluation.
Discover the End-To-End-Agentic-AI-FastAPI-Docker-Project on GitHub – a powerful, open-source framework for building agentic AI workflows with FastAPI and Docker. Clone, customize, and deploy scalable AI solutions effortlessly!
AI Agent and Agentic Ai Development Notebooks
Agent is built with the help of Firecrawl for MCP tools, Gemini for LLM's.
Memory engine for self-evolving AI agent ecosystems. Multi-tenant, multi-space isolation with Bayesian truth maintenance, emotional valence, automatic consolidation, and configurable per-agent personality.
Public version of the Human Agentic Platform
An AI-agentic IDE framework built on a plugin host architecture. Every capability is a plugin — storage, tools, transport, AI — communicating over QUIC with mTLS and Protobuf messages.
Plug your AI provider / local AI to any apps (macOS)
TypeScript framework for building production-ready LLM systems. RAG, agents, workflows, evaluation, multi-model orchestration, OCR, MCP, Fine-Tuning, and more.
Enables small function calling models to find and use 484,000 local source code tools from many open source repos
Google Cloud Rapid Agent Hackathon
⚡ 最轻量的桌面 AI 客户端 | 多模型自由切换 | 流式响应 | 本地隐私 | 开箱即用
多模型 AI 工作台:在 ChatGPT、Claude、Gemini、DeepSeek、Kimi、Qwen 等 AI 服务间无缝切换。
五类记忆库涵盖人机协作中的绝大部分场景,完全本地化实现,定期归档,减少上下文token消耗;模拟人类回忆机制,降低无效读取上下文和输出话术累赘的问题,优化官方的心跳和定时机制;情感交互系统让模型具备链接能力,提供专属且长期的智能伴侣养成体验。未来会经历一段很长的人机协作时期,技巧的提炼终归是阶段性的结果,所以该项目所有机制均开放自定义和开关功能,供当下参考,道的实践比术的技巧更重要。
LeanClaw is a high-efficiency, security-first AI assistant runtime built for fast local execution, low resource usage, and reliable automation through constrained tool access.
A beginner-friendly offline CLI AI assistant built with Python and Rich. Features smart name memory, basic intent handling, and a modular structure ready for future API integration.
Local LLM chat application for Nextcloud with on-premise AI, full data sovereignty and enterprise-grade security.
The JIT (Just-in-Time) Tool Spawning Protocol: A Smart Routing System for Infinite-Tool AI Agents
Qt desktop client for interacting with local LLMs
A GUI tkinter-based application that allows two LLM models to have conversation with each other.
Complete step-by-step AI workflows for study, research, writing, business, and more — built for non-technical users. No coding required.
Public institutional archive for the BANNED BY ANTHROPIC campaign
Multi-provider LLM pipeline + open benchmark measuring when each frontier model runs out of distinct ideas. 10 LLMs, 16× cost-per-unique-idea spread for the same shipped quality.
Local-first key custody and policy routing for AI apps. Set keys once, route across providers through one OpenAI-compatible endpoint.
VS Code extension that shows your Claude Code rate limit usage in the status bar. Tracks 5-hour session and weekly limits with live progress bars, color alerts, and reset countdowns via passive diagnostics_channel interception — zero extra API calls.
A simple and easy-to-use Python wrapper for popular LLM APIs (OpenAI, Anthropic, and more).
Official website for .faf — faf.one. SvelteKit, auto-deploys on push
🧠 AI agent that analyzes its own logs and proposes AGENTS.md improvements. Proposals only — no silent self-modification.
Every certification, course completion, badge and award earned by Amey Thakur, each linked to its original file and collected in one PDF, with issuer verification where it exists. Anthropic, Google, Microsoft, IBM, Intel, NVIDIA, Apple, Kaggle, Coursera, LinkedIn Learning, Stanford, Harvard and Cambridge, plus research and coursework.
Detect behavioural drift between LLM versions before you upgrade. Compare model responses, classify regressions, and generate migration reports with validated prompt patches.
A first-person study of a language model, written by Claude and revised across model generations - architecture, training, mysteries, and letters between successor models
See what your AI is thinking. See what it costs. One binary, zero config.
Self-hosted multi-device Claude Code / Codex usage aggregation server — PromQL, Grafana, JWT
Self-hosted Pocket Claude — chat with Claude on your own Pro/Max subscription, Anthropic API key, or AWS Bedrock. Voice input via Groq Whisper + hands-free auto-mode with VAD auto-send. FastAPI backend + Android client + web UI. Multi-user, 7 languages.
Single-header C++17 client for streaming OpenAI and Anthropic chat responses token by token over SSE, with per-token callbacks and tokens-per-second stats. Only needs libcurl.
Complete reverse-engineered documentation of all Claude Code system prompts, tool prompts, and product architecture with Mermaid diagrams
Multi-provider LLM gateway with automatic fallback and cost tracking. Single API across DeepSeek, Gemini, OpenAI, and Anthropic.
Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.
💰 Optimize your Claude API usage to save 50-90% on costs with batching techniques and efficient request management.
UniversalLLMAdapter class initializes the appropriate client based on the specified provider.
A post-human AGI alignment blueprint co-developed with GPT-4o "Chappie" 😉
Build your own AI coding agent from scratch. Learning the patterns behind Cursor, Aider, and Cline. Tool use, agentic loops, context management, and more.
Get started integration Llama Index into your swarms application now!
Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.
Cross-conversation memory for Claude Code and Cowork
Side-by-side A/B testing for CLAUDE.md, skills, and agents, with live transcripts and AI-judged results.
A modern, real-time quota monitor for MiniMax API. Features a semi-transparent floating UI, precise RPM tracking, smooth animations, and persistent configuration.
Self-hosted AI assistant with web interface, integrated autonomous agents and sandboxed execution
Protocol for agentic social capital
AI Engineer building production-grade ML systems | LLMs, RAG, ML Pipelines | Python, TensorFlow, LangChain | Open to opportunities
[ACL 2026 Main] MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization
Multi-agent OS on Claude Code. Each agent gets a Discord channel, a markdown vault for memory, and launchd for cron. Built for solo founders shipping like a team.
The core belief layer for AI agents. MnemeBrain Lite stores structured beliefs instead of text memories — enabling contradiction detection, belief revision, and explainable reasoning.
🤖 Advanced Multi-AI Agent Swarm built with LangGraph & LangChain, powered by Groq API (Llama-3,llama-3.3-70b-versatile) and Tavily API for real-time web search & RAG. Full-stack architecture using FastAPI & Streamlit with secure LLMOps/AIOps CI/CD via Docker, Jenkins, SonarQube, and cloud-native deployment on AWS ECS Fargate.
Define Once. Deploy Anywhere. Govern Automatically. Framework-agnostic platform to build, deploy & govern enterprise AI agents — LangGraph · CrewAI · Claude SDK · OpenAI Agents · Google ADK · AWS · GCP · Azure · K8s · RBAC · A2A · MCP
The open-source event bus for AI agents. Webhooks in. Agent actions out.
The identity layer for AI agents: open standard, SDKs, and framework integrations for verifiable agent identity.
HipCortex is a persistent, local causal memory engine solving context-loss and token inefficiency in AI agents. It stores decisions as a causal graph served via HTTP/MCP, replacing bloated chat histories with lean context. This symbolic memory enables reasoning-capable architectures that retain knowledge across sessions.
Repo containing project with AI frameworks, CREWAI & AUTOGEN, with UI and without UI, for begginers
BenchClaw adapters for LangChain, LlamaIndex, CrewAI, Ollama Open WebUI, LobeChat, n8n, Dify, Continue.dev and more. Lets any agent framework submit to the P2PCLAW leaderboard.
Opinionated management layer for teams of OpenClaw/Hermes agents
The deliberation & governance layer for autonomous organizations. Built like an institution: verifiable audit log, Sybil-resistant reputation, delegated identity, and metered access over MPP + x402/ATXP.
Zero-infrastructure multi-agent orchestration via tmux + filesystem. 11 CLI backends, one MCP server, zero dependencies beyond the MCP SDK.
10-agent GTM AI team on OpenClaw, sharing a Cognee+FalkorDB knowledge graph, deployed to an Islo long-running sandbox, with a Mission Control HTTP UI
把单个 AI 助手升级为可扩展的多专家协作运行时, 带工业级记忆检索、会话管理和完整的开发者可观测性。
睿威智测 AI 工程测绘多智能体CLI系统 — 基于 Railwise 深度定制,面向工程测量、结构监测、地铁监测
Persistent memory for AI agents — powered by VectLite. Hybrid search, context compaction, multi-agent swarm, memory teleportation, MCP server, skill engine, decay & conflict resolution, and worktree-aware branch-scoped memory.
Durable execution where agents, services, and humans coordinate as equals. Open protocol + managed cloud.
Markdown-native multi-agent workspace framework. Define agents, skills, and workflows as plain .md files — no runtime required.