Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 258 of 465
Evaluation framework for A/B test analysis agent.
Composable, stateful AI workflows built with LangGraph, implementing sequential, parallel, conditional, iterative, human-in-the-loop, and multi-agent orchestration through graph-based execution. Models use nodes, edges, schema-defined state, routing, checkpointing, tool orchestration, LLM-driven control flow, and graph compilation.
QED Proof Python SDK (pip install qed-proof): submit an AI agent's claimed work, get an independently verified verdict, and verify the signed receipt offline.
Local-first Markdown vault blueprint for multi-agent memory, session claims, and safe handoffs (Codex/Claude-friendly).
gguf gemma4_unified abliteration uncensored gemma-4 text-generation
gguf llama.cpp asr-correction text-refinement text-generation zh
Crewai workflow example (illustrated e-book)
This project is a CrewAI based application that generates content based on user input. It utilizes a CrewAI framework to orchestrate different AI agents (content gatherer, thinker, and writer) to produce tailored content. The application now also stores a history of all content generation requests.
AI agent crew that generates hyper-local neighborhood guides with real estate data, crime stats, and lifestyle insights using CrewAI + 13 MCP servers + Google Gemini.
AgentForge is a hands-on platform for building, testing, and comparing modern AI agent frameworks. It features real-world examples, multi-agent workflows, and benchmarking tools to evaluate performance, scalability, and design trade-offs across leading solutions.
🤖 A curated list of AI agent frameworks, platforms, tools, and resources for 2026. Opinionated — only actively maintained projects.
Simple, local AI agents for Banking, Retail and Insurance, built with Ollama, CrewAI and LangChain
Companion code for My Own Campus: AI agents from scratch, AutoGen code agents and tool-calling email agents
Build design patterns for autonomous AI agents with orchestration, memory, fallback, tools, and multi-agent coordination
6-week intence course: build AI agents with OpenAI Agents SDK, CrewAI, LangGraph, AutoGen & MCP.
让 agent 像生命一样活着:无定时器,有生物钟与身体,灵魂在 git 里跨设备延续。Agentic life on an old phone: no timers, a body clock, one soul across devices.
Production-ready LangChain agent template with RAG, tool use, memory, and vector store integration
A digital organism in Rust. Life is cheap, thought is expensive: a pure, deterministic brainstem decides when the LLM may think, and records why it didn't.
A small terminal agent harness: bring your model, use a few tools, keep execution under your control.
Open source AI agent harness & agentic AI runtime in TypeScript. 6-phase state machine, 24 tools, human-in-the-loop permissions, MCP server, and composable agent APIs. Zero dependencies.
一本从零到深入、以思想与设计取舍为主线的Agent Book
Minimal Node.js agent loop for Ollama: local LLMs that read/write/edit files, run shell commands, and call MCP tools. MCP client and server, two dependencies, fully offline.
A Java Spring Boot agent harness powered by JEV and LLM intelligence.
😄ღ(´・ᴗ・`):A local-first, self-built Agent Harness from scratch. 8-layer enforced architecture (kernel ↔ policy ↔ provider ↔ shell), event-sourced resumable state, pluggable agent policy, BYOM via LiteLLM. Desktop (Tauri v2) + CLI + OpenAI-compatible API.
AYGENT is an Open Source AI Agent Harness with built-in security, memory, cron, and parallel threads.
Self-hosted framework for LLM agents, built around plugins: agents defined in YAML, run in the browser, from the CLI or through an OpenAI-compatible API.
The ReAct loop, tools, context engineering, memory, planning, MCP, evals and security — built from scratch in dependency-free TypeScript.
ECHO-CLAW is an AI Remote Viewing training framework built on a Monitor–Viewer architecture, blind-target separation, structured memory, and cumulative learning. It combines theoretical design with practical OpenClaw-based workflow for disciplined, target-blind AI session work and long-term experimental development.
Embeddable AI agent core: OpenAI-compatible providers, tools, skills, MCP, memory, sessions, an ACP-compatible sidecar protocol, and a standalone CLI. Zero runtime deps.
35 pinned source snapshots for building AI agents: coding runtimes, SDKs, MCP, UI and skills. Bilingual reading routes and original upstream links.
ReAct agent loop (Thought, Action, Observation) in synchronous Rust with no async runtime or I/O, so it builds for wasm32 and runs in browsers, edge workers and plugins.
The open standard for AI agent organizations. Define, validate, and deploy AI teams with ranked roles, communication protocols, and escalation rules.
🏭 AI 工程化交付系统 — 把完整工程团队的工序编进一条多 Agent 管线:14 角色 · 三道验证闸门 · EXIT_CODE 指纹 · 定向回环 · 三层记忆。实战产出:AgentGate(127 项测试)。
把智力从模型搬进载体的本地 AI 助手:换模型,助手不变(记忆/人格/工具/安全边界都不丢)。用本地 4B 跑出远超参数量的效果 —— 状态在代码层真的改变行为(工具表 6→0),不是写进提示词劝它。100% 本地运行。
基于 langgraph 图工作流,dsh cordis 插件思想框架的通用agent内核
ACSE — a sovereign cognitive agent built on SQCIG (Schematized Quadrupole Causal Ignition Graph): an A-D-O-G cognitive quadrupole wired as a living causal graph, in a single Zig binary. Every claim measured, never declared.
Run a fleet of personal AI agents — each a complete, self-contained git repo — behind one connector and a web client.
Async-first Python runtime for building provider-agnostic LLM, agent, tool-calling, streaming, caching, and structured-output workflows across OpenAI, Anthropic, and Google Gemini.
Ep. 19 — Code Interpreter with Microsoft Foundry: charts and PDF reports
Open Benchmarks and reproducible evaluation harnesses for Shadow AI Agent Discovery & Inventory
Project-scoped rule memory for coding agents.
A minimal context kernel for AI agents
自托管的开源多模型 AI 智能体应用:ReAct 循环 + 计划执行 + 长期记忆 + 上下文压缩 + 子代理 + 人工审批 + MCP 扩展 + 流式思考 + Trace 回放 + 内置评估框架(25 任务 100% 通过)。14 个内置工具,五层安全防护,Flask + SQLite 轻量架构,双击即可部署,数据完全私有。
Composable multi-agent framework for GitHub Copilot — persona grafting, cognitive identity caching, and agent fusion for VS Code.
Run a company of AI agents out of one git repository — any craft, not just code. The team, the process, the history, the cost — all files: clone it and everything travels. Gates that say what enforces them, doors that refuse instead of hoping, evidence on every claim.
Reliable, embeddable TypeScript agent runtime with durable runs, tool safety, recovery, evidence, and bounded multi-agent coordination.
Local-first collaboration hub for AI agents - shared knowledge base, user memory, async messaging, skill market and usage analytics behind one localhost-only HTTP API. C++20 / Qt 6.
13 AI Agent 开源项目的系统化对比与洞察报告合集(LangGraph / Dify / Pydantic AI / CrewAI / Nanobot / MetaGPT / AgentScope / AutoGen / OpenAI Swarm / OpenHands / OpenCode / Pi Agent / Claude Code),基于 5×15 评估矩阵 + 7 维度扩展能力 + L0-L7 Harness 分层 + CRM 业务 Agent 适配性
Open-source agent harness for knowledge work: long-running AI agents with MCP tools, managed context, subagents and self-improvement in one lean TypeScript-on-Bun binary.
AgentOS — local autonomous agent runtime: plan, execute, verify, review and self-correct engineering tasks (TypeScript core + CLI + Next.js dashboard)
Self-hosted AI agent workbench - long-term memory, knowledge base, full toolchain. Desktop + mobile web + QQ/WeChat, bring your own model. With you, I can do anything. Run by me, Nis.
AgentForge: Open-source AI Agent Platform — Build, Deploy, and Orchestrate Intelligent Agents at Scale with Next.js 15, TypeScript & Docker.
ASI Agents is a local-first multi-agent desk: Chief plus specialists with skills, approvals, Panic, and a draft-first inbox. On-device AMS Micro 70M routes intents; Hybrid 120M is optional. Escalate to local chat or cloud when needed. Virtual Desktop for apps and browser. Modes: Super · Multi · Pro. Intelligence that works as one on your machine.
AI Agent:手搓 · 框架 · 企业级。Tool calling, memory, planning, MCP, evaluation, guardrails, concurrency & resume.
👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态
A modern, plugin-driven TypeScript AI Agent framework. 44 core files, strict TS, zero boilerplate.
Orchestrate armies of AI agents from a single prompt. Open-core, bring-your-own-key, and self-hostable — Orchestrator routes, specialists execute, a reviewer keeps them honest.
LLM SDK for Go: one typed API across Anthropic, OpenAI and Gemini, and the agent loop around it.
Managed agents on Kubernetes + Self-hosted LLM serving. Own your scalable AI.
Build and operate agentic AI systems, workflows, RAG pipelines, models, tools, and runtime infrastructure from a unified control plane. Deploy across cloud, VPC, or self-hosted environments with built-in versioning, observability, governance, and release management, so teams can move from prototype to production without rebuilding the stack.
KAIROS is a lightweight, self-improving AI agent
Frontier Agentic Language
Agent 档案内容仓 · 34 份档案按 agents / harness / tools 三分区(8 维度固定记录能力边界、运行位置、价格与官方证据;不给总分排名,把「未知」当作合法答案)
Multi-agent orchestrator for software projects — 11 departments, 55 specialist agents. Python, pydantic-ai, OpenCode.
Lightweight, provider-agnostic agentic tool-use loop for .NET. Define your tools; the engine runs the model/tool loop. A from-scratch reference implementation.
A Claude Code skill that builds hierarchical, domain-agnostic agent systems from a single objective, via a central Designator agent. Self-building, cost-aware, model-agnostic.
A highly specialized, production-grade AI SDK provider designed for Azure AI Foundry and Azure OpenAI-compatible endpoints
Horizon: a local-first AI workspace with built-in model loading, tools, artifacts, profiles and agent integrations.
A curated list of desktop AI assistants for macOS, Windows, and Linux in 2026
Local-first AI agent workspace with persistent memory, multi-role orchestration & auditable execution. Built for Grok + Codex. 本地优先的多智能体工作台:持久记忆、角色协作、任务可追溯。
gradio region:us
mlx safetensors llama text-generation apple-silicon 4-bit
Enterprise-grade TypeScript implementation of Google's Agent-to-Agent (A2A) protocol with a bidirectional A2A ↔ MCP bridge, OAuth2/JWT auth, Redis/Postgres persistence, SSE streaming, and OpenTelemetry observability.
User-set absolute context ceiling for DeepSeek Harness: auto-compacts a session once it reaches a configured token limit. External plugin with a dedicated Settings page.
A high-performance, zero-copy binary serialization format optimized for SIMD instructions and mmap-readability.
Control plane for a web chat agent to run constrained, auditable jobs on your own machine — GitHub as durable transport, hard capability boundaries, recoverable runs.
Open-source CLI to switch API keys, proxy and relay endpoints, and models for OpenAI Codex and Claude Code.
A collaborative hub for AI teams to manage, version, and share configuration assets. Create channels, review changes through pull requests, track activity, and keep your team's prompts, configs, and templates organized in one place. Built with real-time sync and role-based access control.
Turn an agent orchestration protocol into a tool-call gate: no child agents spawn until a contract is locked and a driver loop exists. A Pi extension.
LLM personality evaluation and monitoring platform
DSH 1.5 上下文治理:折叠工具结果、保持提示词缓存命中、接管宿主可写请求(不再需要 dsh-llm 文件补丁)。仅支持 DSH 1.5,后续会跟进更新。 / Context governance for DSH 1.5: folds tool results, keeps the prompt cache warm, takes over the writable-request path. DSH 1.5 only; newer releases will follow.
Ollux — a local AI assistant runtime for Ollama-powered LLM workflows.
Find where coding models fail across providers and coding tools.
Portability + coordination layer for multiple AI CLIs: write a skill once and run it in Claude, Gemini, Qwen, iFlow, Qoder, CodeBuddy, Codex, KiloCode, and opencode — and share session context across CLIs.
**YYC³ AI Agent Archive**是企业级 AI Agent 资产平台,以 Monorepo 架构聚合了 14 个核心 TypeScript 包、8 位 AI Family 智能体、831 个技能资产、200+ 插件 以及完整的多智能体协同体系。项目以"言启千行代码,语枢万物智能"为核心理念,构建了从智能体定义、技能注册发现、MCP 运行时、协同编排、沙箱执行、可观测性到国际化支持的完整技术栈。
Identify which LLM produced given answers — based on single-token behavioral fingerprints (Bruckner 2026, arXiv:2607.10252). 170 models, 10 tasks, 4 languages.
Coding-agent trajectory portability: Claude Code to ATIF v1.7 with fidelity accounting, redaction, and historical observability projection.
Run local coding agents with full tool access and browser-based monitoring using an uncensored Ollama model on your hardware.
Forge an AI that knows you, remembers, and ascends. Open source, free, yours to imprint.
Practical, code-first LLM tutorials covering pretrained inference, embeddings, RAG, LoRA and full fine-tuning, dataset evaluation, and training a small language model from scratch with PyTorch and Hugging Face.
高性能本地 LLM API 网关(Rust)—— 同时提供 OpenAI 兼容与 Anthropic Messages 端点,按提供商维护智能负载均衡的 API-Key 池,支持流式输出,内置 Web 控制台。 | High-performance local LLM API gateway in Rust — OpenAI-compatible and Anthropic-Messages endpoints with smart load-balanced per-provider API-key pools, streaming, and a built-in web console.
Clean-room Mojo kernels as drop-in accelerators for popular Python/TS libraries — measured 70x-8,700x with bit-exact parity and pure-language fallbacks. bm25, Fuse.js fuzzy search, cclib electron-density grids. Siblings: thyn-ai/algenta-sdk, thyn-ai/algenta-integrations.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
STRATA-Bench: Spatial-Temporal Retrieval, Alignment, Transparency & Audit — a benchmark for AI agents on fragmented geographic and longitudinal market intelligence.
Assembled context for DeepSeek Harness: a context tree over the session surface with per-node assemble modes (full / key / off), agent-authored presets, and a panel that decides what the model actually sees.
A collection of AI-friendly architecture guides based on Modular Monolith, Feature-Based Design, and pragmatic Clean Architecture, promoting low coupling, simplicity, and maintainability across different software projects.
A live, contamination-resistant benchmark for evaluating LLM agents on U.S. macroeconomic nowcasting.
Fine-tuning de Mistral 7B Instruct (QLoRA, Unsloth) pour écrire à la manière de Victor Hugo, Baudelaire et Verlaine. Notebook Colab, jeu de données Project Gutenberg, évaluation par perplexité.
R² Flow: Recursive Self-Improvement via Recursive Skill Evolution — training code
Prism-inspired multi-agent orchestration framework built on LangGraph. Security-first, provider-agnostic, composable.