Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 108 of 465
A self-hostable base for building and running custom agents that's heavily inspired by Claude Code on the web.
Medusa Skill Framework for AI Agents.
Open source framework for evaluating AI Agents
Lyzr Agent Framework is the first and only agent framework to natively integrate Safe AI and Responsible AI modules in its core agent architecture
AI Memory System - Consciousness continuity through intelligent memory curation and retrieval
Azure Animations, where we make hard-to-understand Azure cloud concepts easier and more fun to learn!
First Latency-Aware Competitive LLM Agent Benchmark
Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability
TaskForge Platform runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) through a human-in-the-loop approval process. Every approval triggers a container image rebuild, and every LLM interaction is logged for audit.
Code for the RA-L 2024 paper "Contingency Games for Multi-Agent Interactions."
Go SDK for Claude agents
Founder-first meta-layer to generate production-ready OpenClaw multi-agent setups from one prompt: agents, skills, workflows, memory, and install docs.
This repository provides a comprehensive starter kit for leveraging GitHub's GPT-4o AI models with Node.js.
Full stack observability for local AI agent development. Provides a llm-proxy to use as LLM provider base URL, logs traces to opik.
🎯 Three-layer prompt composition system for AI agents. Translates numerical weights into semantic priorities that LLMs actually follow. ⚡ Framework-agnostic, open source, built for production multi-agent orchestration.
Minimal runtime for Recursive Language Models (RLMs) inspired by the MIT CSAIL paper "Recursive Language Models".
Markdown-Native Multi-Agent Task Coordination
Recovery-Bench is a benchmark for evaluating the capability of LLM agents to recover from mistakes
AgentOS is a lightweight, single-file implementation that provides a robust foundation for building autonomous AI agents. It implements the core concepts outlined in Karpathy's Agent OS architecture while maintaining simplicity and extensibility.
macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.
Aqueduct is a simple yet fully-featured AI gateway built on top of the LiteLLM Router SDK using Django.
A complete, hands-on roadmap to becoming an AI Engineer, from Python basics to production RAG, Agents, and Fine-Tuning. 10 modules, 20+ notebooks, 15 real projects. Free, open source, built for the community.
Agentic AI Agents, LangChain v1, Gemini 3, Tool Calling, Agent Memory, Prompt Engineering, Guardrails, MCP, FastAPI
Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.
⚡ Production-ready LangGraph interrupt template with modern web interface | Human-in-the-loop AI workflows | FastAPI backend + Next.js frontend
Single-file web UI for NVIDIA DGX Spark — pull Ollama models, browse and download from HuggingFace, manage LiteLLM routing, and control SGLang, vLLM, llama.cpp, LocalAI, and ComfyUI. All from one browser tab.
AI agent engineering meets system design: Claude Code dynamic workflows, loop engineering (bounded evaluator-optimizer gates) and runnable workflow scripts, plus real-world architecture case studies (Uber, Netflix, Stripe) and 15 engineering-blog deep dives, as Mermaid and draw.io diagrams.
基于 Tauri 2 与 Vue 3 的 AI Agent 桌面工作台,支持本机或云端 HexClaw 服务,集成多模型对话、知识库、工具、任务自动化与作业辅导。
260+ curated tools, guides, and projects for turning an Apple Silicon Mac mini into a 24/7 agentic AI home server. Ollama, Claude Code, Jellyfin, Vaultwarden, Home Assistant, and more - with one-command installers.
可自托管的 Go AI Agent 服务,集成多模型、工具调用、RAG 知识库、长期记忆、MCP、技能和任务自动化,支持桌面客户端、API 与多平台 IM 接入。
Run Hermes Agent + Claude Code locally on llama.cpp — zero API costs. A 4h / 7M-token session that would have cost $94 on Claude Opus 4.7
mori MCP server — a governed memory layer for AI coding agents.
Economical human-readable logs and structural (event pattern) retrieval for agentic trajectories
跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot,你只需要跟飞书bot聊天他就能帮你干活了
Official documentation for Taskade — build apps, deploy AI agents & automate workflows on the AI-native platform. REST & Action APIs, MCP server, Genesis. Source for docs.taskade.com — typos & gaps welcome via issues/PRs.
WebLLM Gateway:让 Qwen/DeepSeek 网页模型接入 OpenAI/Anthropic 兼容 Agent 工具链,支持 OpenClaw、Hermes、Claude Code、Codex 工具调用
[ICML 2026] E-mem: Multi-Agent Based Episodic Context Reconstruction for LLM Agent Memory
AI toolbox for grounding LLMs on Langium DSLs with evaluation, constraints, and agent skills
🏖️ The Multi-Agent Terminal Office
Transparent logging proxy for LLM API traffic that auto-configures clients and records every request and response to Claude, OpenAI, and other providers for debugging, auditing, and analysis.
An Agent with Semantic Memory. This is an experiment for Neuro-Symbolic AI
Open-source AI gateway on Cloudflare Workers, in TypeScript: OpenAI/Anthropic-compatible chat with SSE streaming, Files + Batch APIs, provider routing with circuit breaking and failover, virtual API keys, per-tenant Durable Object storage, quotas/wallets/budgets, guardrails, response cache, MCP server, durable metering, contract-driven Admin API.
Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.
gradio region:us
gradio region:us
streamlit region:us
docker region:us
transformers safetensors mixtral text-generation function calling function-calling
transformers safetensors llama text-generation conversational tr
gradio region:us
transformers safetensors phi4mm text-generation nlp code
transformers pytorch llama text-generation code math
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage (ACL 2026)
The black box for AI agents — record every session, referee every task claim. Live mirroring + atomic coordination in a bucket YOU own. No server.
Digital Life · Life Engineering — A runtime framework for persistent, autonomous LLM agents
Event-driven long-horizon memory for real-time wearable AI and LLM agents.
Your Hermes agents, one shared brain.
Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.
Learn Codex
transformers safetensors mistral text-generation conversational en
200+ AI, Gen AI, LLM, agentic AI, Forward Deployed Engineer (FDE), AI systems architect, applied AI, LLMOps and AI platform engineering interview questions across 10 topics. Each has a short answer, in-depth detail, a worked example and interview tips.
CPU-oriented Python library for discrete Active Inference experiments in radCAD and cadCAD: deterministic grid worlds, multi-agent transitions, generative-model helpers, and fail-closed validation.
Pre-merge behavioral regression gate for AI agents. Check agent changes, inspect regressions, and block broken behavior before merge. Local-first.
AI Agent / LLM application engineer Chinese interview question bank: 2,038 questions with reference answers
This project is a simulation of the Magi System from the Neon Genesis Evangelion series. It uses the crewai package to create agents that represent the three supercomputers of the Magi System: Melchior, Balthasar, and Caspar.
A TUI agent orchestrator for power users.
Local-first Electron cockpit for the Codex SDK, OpenRouter, multi-agent crews, and bounded computer access.
Autonomous agent loops for Hermes Agent: the autoresearch harness and the health/improvement maintenance loops.
A modern full-stack personal website and content management system built with Next.js and Hono, featuring a monorepo architecture powered by Turborepo.
A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.
⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and human decision-makers to co-exist in a multi-agent environment.
Karpathy's LLM Wiki pattern as a minimal, agent-agnostic skill
gguf llama-cpp ollama moe qwen code
A stress-testing benchmark for partial-completion evaluators in stateful multi-turn agents, focusing on temporary progress, rollback, and attribution failures.
Multi-language Active Inference framework combining ant-colony-optimization-inspired multi-agent simulation with variational message passing, implemented across 50 programming languages for research and benchmarking.
Run LangGraph and LangChain apps behind a FastAPI runtime with a standalone agentseek-api CLI
Add an agent to your app in minutes
Open-source AI agent framework for PHP. Tools, memory, security guards and a ReAct loop built in. Works with Laravel, Symfony, WordPress, Drupal, Magento, Joomla, OpenCart, PrestaShop. Any LLM provider. MIT.
A platform creating fully autonomous Hermes agents for your team.
See how sure an LLM is about each word.
OpenTelemetry tracing for DeepSeek Harness (dsh): turns each agent turn into a GenAI span tree — steps, LLM calls with TTFT, tool executions, token usage — exported over standard OTLP to Jaeger, Grafana Tempo, SigNoz, Langfuse, or any compatible backend.
PMX Canvas is a shared board where you and your AI agents collect and present the data and evidence behind your work. Curate that material into context for your agent's next step, then bring the results back onto the board to review and build on. You both add and edit material on the same board, in real time. Pin context to focus input and output.
⚡ Terminal HUD, hard budget breakers & prompt-cache leak alerts for AI coding agents (Claude Code, Cursor, Codex)
Argolink-focused agent workflows and provider-neutral integration for GPT-6 Sol.
Coordinate coding agent teams from GitHub issues to reviewed pull requests, with a local dashboard for progress, decisions, and human oversight.
本项目是一个系统化的 LangChain AI Agent 学习教程,涵盖从零基础到生产级应用的完整路径。项目包含 33 章学习文档和 77 个可运行示例代码,按九大模块递进组织:基础入门、核心机制(Chain/RAG/Memory)、Agent 构建、LangGraph 进阶、生产化实践、模型微调、评估优化、实战案例及服务化部署。默认使用 GLM(智谱 AI)作为 LLM 提供商,同时支持 DeepSeek 和 Qwen(通义千问)。每个章节配有概念讲解与动手实践,适合有 Python 基础的开发者在 8-9 周内系统掌握 AI Agent 应用开发。
Autonomous framework for long-running agents: a charter guides Claude Code, Codex or Pi through an actor, critic and scribe loop for hours.
降低 LLM 角色扮演中软拒(soft refusal)与空回(empty response)的思路手册。核心:攻击外审模型注意力。纯文档项目,可在任意 Agent 框架复现。灵感来自类脑社区酒馆预设。
非技术产品经理/学生从想法到上线的 AI 产品开发工具包(规则卡 + 三份技术手册 + 操作手册)
A self-organizing swarm of AI agents with no leader: shared task board, git workspace, agents that write their own MCP tools, and the swarm itself as an MCP server for Claude Code.
Code for "EvoTeam: Multi-Agent Collaboration via Evolving Teams"
Light but flexible templating and FSM framework. This repo is @promplate itself.
Official Repo for Chat AI
This is an official implementation of the paper ``Building Math Agents with Multi-Turn Iterative Preference Learning'' with multi-turn DPO and KTO.
Multi-Model Collaboration Pipeline — orchestrate AI models as a DAG. RL routing, multi-verifier voting, agent mesh, self-improving. Works with OpenAI, Anthropic, Gemini, DeepSeek. npm install mmcp-core | pip install mmcp-core
Chat component for Python Dash
A collection of info about plugins for ChatGPT from OpenAI.
Proximal Policy Optimization with Beta distribution - uses multi agent Unity ML Tennis
A Continual Multi-agent RL testbed based on Hanabi