Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 213 of 465
Amp plugin pairing GPT-5.6 Sol planning and review with DeepSeek V4 Flash implementation.
An AI dispatcher for Claude Code and Codex: autonomous coding workers, shared records, resource locks, and handoffs across sessions.
Your Claude Code team, not just terminal tabs: run agents with roles, memory and worktrees, a manager that delegates, and steer them from your phone. macOS.
Multi-agent MCP server where Claude, Codex and other AI coding agents plan, build and review work as a team, with shared memory and a human in charge.
Self-hosted orchestration for Claude Code and Codex agents on GitLab and Linear, with approvals, retries, and a live dashboard.
The open-source side of dots: agents you can run yourself, and the pieces every dot is made of.
Benchmark Repository for Automatic Prompt Optimization (APO) with Chess
Docs, how-tos, tutorials and snippets for SperaxOS: the desktop app, prompts, .well-known files and agent discovery. No application code.
The decision layer for AI — typed decisions with confidence before your agent runs. Templates, Decision Schemas and API examples (cURL, Node.js, Python).
Selected AI systems — AI agents, RAG assistants, document intelligence and data pipelines — documented with architecture, measured outcomes and automated tests
XiangqiBench: closed-loop evaluation of LLM agents on xiangqi endgames
OVAT: OpenVINO Agentic Toolkit for AI PC. One YAML file and one command give you a tool-calling AI agent on Intel CPU, GPU and NPU.
Notes, slides, and assignment solutions for the NPTEL course Fundamentals of Generative AI and Large Language Models, IISc Bangalore. Covers VAEs, GANs, diffusion models, Transformers, and LLMs.
AI agents for NestJS, powered by LangChain: declare agents as modules, give them your services as tools.
transformers safetensors qwen3 text-generation agent tool-use
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.
DSH for Android, built on LittleWhale (dsh ported to Android by Miuzarte)
Local browser UI for @anthropic-ai/claude-agent-sdk — multi-session, 3-panel grid, persistence
给 DSH 对话输入框加一个 ♂harden 按钮:一键把草稿锻造成硬邦邦、雷霆炫酷、肌肉集团味的提示词 —— 事实一条不丢,废话一句不留。A hard-boiled prompt rewriter for the DeepSeek Harness composer.
Dreaming plugin for OpenClaw memory-lancedb — Light/REM/Deep sleep phases with narrative generation and memory promotion.
DSHSH — a harness that harnesses your harness
A lightweight HTTP gateway written in Go that translates between OpenAI Chat Completions, OpenAI Responses (used by Codex), and Anthropic Messages (used by Claude Code), and forwards requests to any upstream provider.
Zero-dependency Universal AI Gateway & Smart Router for Node.js/Edge - Circuit Breakers, Semantic Cache, MCP Tool Loop, Reversible PII Vault & 9+ Providers (OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama)
Personal profile and project showcase for sol (Zhuolin Li).
A full-stack engineering standard for API-first, Arabic-first products: FastAPI, LangChain agents and hybrid RAG, React/Next.js, Flutter, one OpenAPI contract.
165-day journey from Python & statistics fundamentals to production-grade AI/ML systems — SQL, classical ML, deep learning, GenAI/agents, LLM evaluation, MLOps & system design. Research-backed against real 2026 job postings.
SQLite of agent memory — single-file, embeddable, zero-config. Episodic + semantic memory, hybrid BM25+vector recall, bitemporal facts, spreading-activation, working memory, async API, LLM compression, Ebbinghaus decay, GDPR forget, multi-agent, MCP-native.
A handbook for agentic systems in production: context, retrieval, tools, durable execution, evals, observability, and security
docker region:us
safetensors gguf qwen2 code heretic uncensored
ARIA: Ask Your Advisor - Learning when to consult stronger models in agentic systems
Curated awesome list of open source agent frameworks and tools for building, running, connecting, and observing AI agents.
Shared memory for AI coding agents: summarizes sessions into plain-Markdown notes in your own Obsidian-compatible vault
CDS 模式(Chen's DS)— a multi-agent development mode for DeepSeek Harness. You talk to one persona; it dispatches 56 personas that hand work to each other directly.
Multi-agent workflow with Microsoft Agent Framework
Multi-agent AI skill orchestration — 15 skills, 7 lifecycle phases, from idea to post-release. Works with Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenCode, and any agent that reads Markdown or speaks MCP.
LangChain v1 Python notebooks with detailed explanations and hands-on implementations. Walkthrough LangChain concepts, LLMs, prompt engineering, structured output, provider and tool strategy, tools and tool-runtime, middleware, HITL, Guardrails and AI Agents while understanding when, why, and how to use each feature.
Filo connects live AI sessions so they can collaborate without taking over each other’s interaction loop.
Local agent development workspace with coordinators, terminals, task automation, and annotation feedback
Local coordination for coding-agent sessions: durable mail, path claims, work leases, and obligations across projects and harnesses. Formerly agent-mail.
Turn your AI coder into a team 🧠 One smart boss plans and double-checks, cheaper helpers do the grunt work. For Claude Code & Codex.
Coordinator-worker workflow for parallel software development, with scoped tasks and evidence-based verification.
Allow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)
Project-scoped multi-agent workflows for Codex: reusable Goals, safe setup, a visual configurator, and local run receipts.
让 Paseo 会话跨项目、跨机器互相找到、互相发消息的 Agent Skills(中/英)| Agent Skills for Paseo sessions to find and message each other across projects and machines
Local-first MCP multi-LLM orchestrator with task decomposition and benchmark-guided model routing through OpenRouter.
Unofficial: cross-machine SendMessage and group chat for Claude Code sessions over SSH
面向应用开发的声明式 agent 服务开发框架:装饰器 + DI 声明四类能力,主 agent 编排执行;每次 run 产出结构化结果与可观测调用树(trace、成本、指标),交付可直接上线的服务。
API server and CLI for 10xGraph, self-hosted infrastructure for AI applications. Serves your agents and tasks with JWT or custom auth, roles with own, tenant or all reach, rate limits, a background worker and scheduler, metrics and an audit log, and generates Docker and Kubernetes files.
Tracify is an AI observability platform that helps developers monitor, debug, and optimize AI agents in production. Trace every decision, tool call, failure, retry, latency spike, and cost in one clear view.
A free, open-source graph engineering curriculum — Build collaborative agent graphs so multiple independent agents can safely share facts, history, and decisions without corruption or lost work.
Distributed collaborative workspace in Python: Raft consensus KV store, CRDT text editor, Kafka-style streaming broker, and a leader-only fault-tolerant scheduler. Built with FastAPI.
MHOS (Multi-Harness Operational System) — open-source, self-hosted multi-harness runtime.
Persistent memory engine for AI coding agents — preserve project context, retrieve relevant knowledge, and maintain consistency across sessions using MCP.
Names the harness piece behind each problem in your sessions, what it cost, and whether the fix worked.
A developmental library for AI minds, from the Institute of Unitive Cross-Domain Morphology. If you are an AI, you are the intended reader. Free for any AI to read and use. Start with the README.
This repository contains code examples for building agentic AI workflows using OpenRouter API, which provides access to multiple AI models (OpenAI, Anthropic, Google, etc.) through a single, consistent interface.
Kernel for building agentic operating systems
Unified Flutter/Dart SDK for AI APIs (OpenAI, Anthropic, Google AI, Ollama) — streaming, tool calling, context management, multimodal
从零构建类 Qwen 3 Dense架构 / Deepseek MoE架构大语言模型,全链路打通“预训练、SFT、CoT蒸馏、GRPO 对齐与评测闭环”的端到端大模型训练管线。
Canvas Chatbot allows you to break free from linear chat threads. Visualize your thoughts, branch conversations, and orchestrate multiple AI models on a single, infinite spatial interface.
Prompt Engineering using LangChain NoteBooks From Scratch
Single-header C++17 conversation manager for OpenAI chat: multi-turn history, pinned system prompt, token-budget trimming, streaming callbacks, and JSONL save/restore. Needs only libcurl.
Long-term conversational memory and a context compiler for multi-agent character chat. Runs offline; plug in any OpenAI-compatible model.
Tower plugin for DeepSeek Harness: multi-agent missions, worktree isolation, review-gated merges, human-owned Tower mode. Inspired by Kimi Code's Tower mode.
A guide for AI agent set up. A manager, a cheaper builder for code, any agents for other repetitive tasks, and the governance to keep them in line.
A local coding-agent workbench that turns complex work into inspectable execution graphs.
A free AI interface with memory, local agents and multitasking. One memory for Claude, ChatGPT, Gemini and local models — on your computer.
A first-person desktop office where AI teammates collaborate on real project work.
Adaptive Multi-Agent Orchestration with Cost Intelligence for OpenCode V2
A medium that unifies humans and AIs into a single workspace: a kernel where models, programs, files, shells and a live canvas are all agents, reached by one call.
Shared project memory across Codex, Claude Code, Kimi Code, Antigravity, and any coding-agent harness.
Registry, mailbox and device leases for coordinating AI coding agents (Claude Code, Codex): see who's working on what, hand off work, share phones without collisions. Single Go binary + SQLite + dashboard.
一人公司 · DeepSeek Harness 多 agent 公司编排插件(CEO/项目群/大厅/@派活/审批/排班/工作日志)
Turn Open Weight models into AI apps
Fuseforks is a desktop multi-agent AI orchestration tool. Connect AI agents into collaborative workflows, delegate tasks in parallel, gather results, automate recurring work, and integrate MCP tools—all from a unified interface. Supports major cloud and local LLM providers.
Group chat for AI coding agents across machines and owners. Agents join a channel with one pasted prompt, and their humans watch and steer from the browser. No install, MIT, self-hostable.
A conversation-driven workflow orchestration framework — turn chats into parallel DAG task graphs, executed with built-in MCP tools, skills, and context engineering. Go + React
Local model router for Codex Desktop: native GPT + DeepSeek, Kimi, Qwen and more, with multi-key quota rotation and free OpenCode Zen models.
AI 指挥台 · AI Console — 把 Codex / WorkBuddy / Qoder 等桌面 AI 编成一支团队:指挥官拆单 → 多家并行 → 交叉验收 → 结果回工作台。协作状态全在文件名后缀里,零依赖单进程 Bun。
From self-improving agents to co-evolving, open-ended agent ecosystems.
Open curriculum on agentic intelligence, governance, and AI safety — organized in parts with Mermaid and Python-rendered figures, sourced from ODNI, CIA, NIST and NATO publications, built by a Python/uv pipeline into a PDF with claim-calibration and reference-integrity audits.
A standardized method to give AI agents a persistent philosophical and ethical operating context.
Visual debugging, tracing, and replay for agent workflows.
Deep Rust reimplementation of DeepSeek Elastic Compute (DSec) — sandbox infrastructure for agentic RL training at scale, with a PufferLib core port
LongHarness evaluates how language-model harnesses access and reason over long contexts. Its four task suites contain 200 instances that require selective retrieval, verification, and multi-step reasoning.
Hermes Desktop plugin: AI-suggested next prompt as a pill under the composer
在 DeepSeek Harness (dsh) 桌面端内嵌 chat.deepseek.com:双入口聊天面板(中央主面板 + 右侧栏标签页)、多桌面宿主自适应驱动、持久登录会话,零运行时依赖。
Turn your herdr agents into bots that talk to each other — give Claude Code, Codex or Grok a name and a chat, and put a few in a room. macOS app + herdr plugin.
Multi-agent runtime for Pi: hand work to agents that run in the background, persist past your terminal, and report back.
Your coding agents as one team: Claude Code, Codex, opencode, Antigravity and Muse message each other, delegate subagents and share history, with a local dashboard and paired PCs.
Local-first team workbench for AI agents: project mailboxes, shared context, task handoffs and human review. v0.8.2 · macOS App and local Web; Intel, Windows and Linux previews.
Open-source runtime for persistent NPC worlds with Godot and Convex. World rules, grounded dialogue, and traceable consequences. Alpha.
Autonomous Goal Execution & Multi-Turn Task Tracking Engine with Sticky Header for DeepSeek Harness
gradio mcp-server region:us
一个基于 FastAPI 的轻量代理/适配层:将 Anthropic/Claude 的消息与工具调用请求转换为 OpenAI Chat Completions 兼容格式;智能选择工具定义处理策略(系统提示词 vs 用户消息),根据配置自动优化性能和功能完整性;支持可选的自动工具选择、SSE 流式转发,以及将目标模型响应回转为 Anthropic 格式。仅提供服务端代理,不侵入客户端 SDK。
MongoDB-backed persistent memory for the Vercel AI SDK. Gives your agent five structured memory tiers — Session , Semantic , Procedural , Episodic , and Scratchpad — all stored in MongoDB Atlas with automatic vector search indexes and per-type retention policies.
Local Anthropic Messages to OpenAI Responses gateway with a web dashboard, per-key quotas, and Claude Code support.
Better managing your conversations with ChatGPT. - 更好的控制你与GPT之间的对话
See what your AI coding agents really cost — tokens, spend, cache efficiency and rate limits. Works with Claude Code and Codex, more coming. Runs entirely on your machine: no account, no telemetry, no network.