Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 124 of 465
Local-first memory context for Pi coding agents.
The field manual for running a real self-hosted AI agent with OpenClaw.
A modular PyTorch library designed for learning, training, and deploying world models across various environments.
BranchContext gives AI agents and automated workflows copy-on-write branching over filesystems and processes
Bittensor Subnet 11: verified agent work on open-weight models. Season 2: fusion policies over the Engy catalog; next: an open protocol for verifiable environments.
Menu bar app for tracking Claude Code & Codex CLI token usage on macOS — animated, live, SwiftUI
Coordinate multiple computers running Claude Code through git-based messaging. Includes Fleet Commander — an interactive browser game to learn the system.
Manage and orchestrate AI coding agents (Claude Code, Copilot, Goose, etc.) on remote machines — task decomposition, multi-agent coordination, and real-time visibility across environments.
Orchestration and memory for multi-agent systems
A beautifully crafted desktop client for running and managing local LLMs via llama.cpp.
[ICLR 2026] A framework to "create benchmarks" and "evaluate AI co-scientists" in experimental data-driven real-world scientific research.
Tool-native dataset generation skill for Codex, Claude Code, and Antigravity with SFT/DPO pipelines, verification, deduplication, and flexible export.
Self-hosted knowledge base and memory for AI agents. MCP server and REST API with hybrid search, reranking and per-user permissions over your files, S3, Azure Blob, GitHub, Confluence and Jira. RAG on .NET 10 and pgvector.
A portable library of reusable AI skills, prompts, workflows, schemas, and automation patterns designed for ChatGPT, Claude, Copilot, and local LLM workflows.
6 progressive demos to detect, prevent, and self-correct AI agent hallucinations, from Graph-RAG research to production deployment on Amazon Bedrock AgentCore
The open-source client-agnostic agent harness
Curated reading list & living survey on long-term memory for LLM agents — 989 papers, 529 archived PDFs, deep notes mapped to memory-kernel modules. Feeds the Ymem Research Radar.
Local-first runtime for managing an AI-company with agents, orchestration, git workflows, and CLI-driven execution.
Governed API and agent runtime for desktop, VS Code, and CLI. Secure API testing, mocking, automation, secret protection, and controlled AI tool access.
Invarium is pytest for AI agents. Test behavior, not exact text.
Multi-provider Android AI chat SDK with Jetpack Compose UI, headless Kotlin API, Room history, and support for OpenAI, Gemini, Claude, and Grok.
An external memory for LLMs: a bi-temporal knowledge graph with hybrid (keyword + vector) retrieval and a self-improving reflection loop. Benchmarked to beat flat vector RAG on corrections and time-versioned queries.
2-in-1 for Claude Code: a live system-tray usage widget (5h/7d plan limits) + local token & cost analytics — per project/model/tool, budgets, forecasts. Unofficial; not affiliated with Anthropic.
Obsidian-powered daily logs, session logs, /prepforreset handoffs, and wiki janitor skills for AI agents.
A self-hosted, keyboard-driven cockpit for running a whole fleet of Claude Code agents at once. Worktrees, command palette, scheduler, voice — every layer stacks, so you ship far more than hand-juggling terminals. Your machine, your keys, no telemetry.
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
Gaia is a living, open registry of every AI agent skill — structured as a leveling skill graph. Live site: https://gaiaskilltree.com/
TypeScript AI agent framework where personality is architecture. Specialists, not chatbots.
多智能体应用与任务执行平台
文 Veyllo Agentic Framework
Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs. Fused semantic + SIMD-accelerated hybrid recall, in-process MCP, REST/gRPC, and language SDKs.
Curated list of Codex pet projects, galleries, tools, SDKs, and desktop companions
AladdinAI: open-source BYOI (Bring Your Own Infrastructure) AI Agent platform. Connect your own VMs, NVIDIA NIM, OpenAI, Anthropic, Ollama — build and manage AI agents visually.
OpenClaw 源码深度研究:27 章技术主线 + 2 月以来 PR 演进 + fork/变种生态 + 缺陷与 roadmap(2026-04 snapshot)
AgentForge a multi-agent AI platform for evidence-backed RAG and verified coding workflows. Built with LangGraph, FastAPI and React, featuring multimodal document analysis, sandboxed coding agents, human in the loop approvals and automated LLM evaluations.
Local-first associative memory and vector search for AI agents, with Rust, Python, Node.js, and MCP integrations.
gradio region:us
gguf glm chatglm thudm quantized GGUF
transformers safetensors gguf llama text-generation mergekit
transformers gguf moe vlm vision agentic
gguf facebook meta pytorch llama llama-3
The Regression Testing Framework for AI Agents. Replay · Evaluate · Assert · Catch Regressions — in CI. Like Jest for your AI layer.
Intent Agent Model (IAM) — Bob reference runtime on Google ADK. Historical V1. IAM = Intent Agent Model, not Identity and Access Management.
Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.
ClawSouls — an open-spec platform for shareable AI agent personas (souls). 80+ curated souls, one-command install, works with any SOUL.md-compatible agent (OpenClaw, Claude Code, Cursor & more). Apache-2.0.
mlx safetensors qwen3_5_moe optiq code text-generation
Open-source control plane for private, governed enterprise AI — one gateway for every model, composable governed pipelines, and apps your whole team builds in plain language, on infrastructure you own.
Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, no vector DB.
Run multiple Claude Desktop instances side by side on Windows, each with its own account/MCP/settings. One click, survives auto-updates.
A memory and continuous learning system designed exclusively for AI — your AI grows smarter the more you use it.
Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.
Open-source alternative to LangGraph Platform for TypeScript — self-host your LangGraph.js agents behind the standard Agent Protocol API. Your infra, your Postgres, no vendor lock-in. Drop-in for the LangGraph CLI.
Portable, hash-verifiable intermediate representation for agent execution trajectories (seals, effects, .tir packages) on top of durable backends like Temporal and DBOS.
DeepSeek Harness (dsh) plugin: silky streaming reveal, no flicker. dsh 丝滑流式渲染插件。
Continual self-evolution plugin for DeepSeek Harness: versioned, auditable, rollback-safe harness state refined from session trajectories, with a benchmark-driven validation loop.
DeepSeek Harness(dsh)的独立非官方原生 macOS 客户端——SwiftUI/AppKit 实现,非 WebView/Electron 套壳,内置 Node + dsh 运行时。Unofficial native SwiftUI macOS client for DeepSeek Harness.
Spam-filtered, open-data registry of DeepSeek Harness (dsh) plugins, bundles, and skills.
Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everything from your host.
A place to evaluate public models
Python SDK for Fly.io Sprites: computers for agents. Sprite management, remote command execution, filesystems, checkpoints, services, and network policy from Python.
Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.
Open-source multimodal AI framework & agent harness — an enterprise AI runtime for building agentic applications over video, audio, images, documents, and organizational knowledge. MCP tools, A2A orchestration, persistent memory, hybrid RAG, GraphRAG, evaluation, guardrails, model lifecycle.
This repository is a comprehensive, hands on roadmap to Python Mastery and AI Engineering. It is designed to take a learner from the very foundations of programming to building professional grade AI agents and scalable systems...
A phone-friendly web interface for Herdr: monitor agents, receive notifications, open real terminals, and send files.
ADE/harness where you manage a team of agents the way a CEO manages a company — agentic mail between workers, a built-in task manager with budgets, git worktree isolation per agent, and cross-model review before every squash merge. Claude Code, Codex, Grok and an OpenRouter harness behind one contract.
Local two-agent collaboration for Claude Code, Codex, and Grok Build. Keep your native sessions and tools; relay, review, and audit in a shared Room.
2 text files and a folder. The ICM Folder System I run several businesses on, in plain English, for people who do not write code.
Live token spend dashboard and notifications for Herdr agent panes
Run claude with rootless podman
Awesome Research Paper List for AI agent harness evolution: Foundation, Benchmark, Recipe, Position
Multi-tenant projects & users plugin for DeepSeek Harness (DSH): per-user symlinked workspaces, login gate, session isolation, workspace-write lock and system-prompt guard
Online explainability for LangGraph agents through counterfactual planning and reasoning provenance graphs.
从零开始学 AI Agent:17 章渐进教程 + 每章可运行代码 + 算法面试轨(100 题详解)+ 65 道模拟面试题 + 项目实战案例(真实 Go Agent 项目源码级复盘,76 道练习题)+ 本地多语言在线判题(Python/C++)。网页版双击即开,无需 API Key 也能跑完。
An agent / harness multiplexer that allows you to access your agents from any device and machine
BrighTO LLM Router: free open-source, ultra-fast Rust LLM gateway/router and LiteLLM/Bifrost alternative with OpenAI + Anthropic APIs, Claude CLI bridge for OpenAI-compatible models, Qwen3.8 dual protocol, model load balancing, fallback routing, team API keys, token budgets, SystemOne decisions for Ollaya/Laya, JEV/DJEV and Quyết.
Behavioral regression testing for AI apps and agents: pytest plugin, behavior diff, CI gate, and document extraction metrics
Desktop monitor for coding-agent activity, provider accounts, and infrastructure resources, with a floating companion.
Plain-language glossary of 153 cloud computing, AI/ML, data and infrastructure terms, also available as JSON.
XTrace Desktop is a free Mac app that shows how productive you are with coding agents. It reads the history Claude Code, Codex and Cursor already save on your Mac and turns it into a dashboard: where your hours went, what each session would have cost at API prices and what the outcome was, and how close you are to your usage limits.
Agent decision replay studio - record a decision, rewrite the policy and diff the replay
Help individuals and teams understand their prompting habits and improve how they work with AI coding agents. Get specific insights into prompt clarity, context, rework, outcomes and wasted effort, plus security flags. Bring your own LLM, no SaaS.
Pipeline engine for multi-agent LLM workflows, with Dippin pipelines, parallel agents, and a terminal dashboard.
Open-source, self-hosted analytics for MCP servers
The experience graph for AI agents. Self-hosted memory, human-reviewed decisions, and outcome-backed datasets for model evaluation and learning.
A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.
Autonomous, local-first multi-agent AutoML platform. Zero cloud costs, zero API keys, 100% private. Benchmarks 7 algorithms, tunes hyperparameters, and serves live in-browser predictions.
点将台:可迁移的 Agent 分层协作编排器。支持任务派发、会话续跑、独立审查、后台执行与用量记录。当前开箱即用为 Codex → Claude Code,可经适配迁移到其他 Agent 组合。
static rl-environment region:us
Self-hosted AI gateway for small teams: a key per person, budgets that fall back to local models, PII masking and free SSO.
Find out which model actually answers your Codex requests (detects silent model substitution, e.g. gpt-6-astra served by gpt-5.6-luna)
🐑 全网 AI/游戏 免费福利活动自动收集 | 薅羊毛 | 代金券 | 免费额度 | Epic免费游戏 | Steam限免 | 华为云/阿里云/腾讯云/百度云/火山引擎/智谱/Kimi/DeepSeek | 大模型免费试用 | GPU免费算力 | GitHub Actions 每日自动更新 | SVG日历嵌入README | OpenAI兼容中转站 | fork即可使用 | 不依赖Pages
Agentic coding framework and meta-harness for planning, building, reviewing, and tuning software across coding agents. Portable agent squads, skills, governed project knowledge, quality gates, and local token observability. Human judgment. Agent speed.
给它一个 PRD、一个需求点子、或一个可落地的 Agent 方向,它推导出架构方案、组件选型与代码骨架,直到一个能在真实环境运行的产品。
Self-hosted LLM gateway: vendor keys, rule-based routing, fallbacks, throttling and usage reporting over gRPC
A hidden Omarchy desktop for your AI agents: they launch, drive and screenshot apps and shell plugins there, never on yours.
⚡ Fastest and lightweight harness for AI agents
DeepSeek Harness绿色整合版,一键安装启动,不污染C盘,一个文件夹里管理,自动更新。DeepSeek Harness Green All-in-One Launcher - double-click to run, all-localized
A modern chat interface powered by the Claude Agent SDK. Real-time streaming, sessions, and specialized sub-agents.