Category

Agent frameworks & infrastructure

46,465 agents

Every agent in Agent frameworks & infrastructure, page 215 of 465

chatgpt-jiangzhi-test★ 5

ChatGPT 降智测试 / GPT 降智检测:一句「鹈鹕骑自行车」SVG 动画提示词,1 分钟判断 ChatGPT 有没有降智(附满血样例与 12 分评分表)

claude-desktop-gateway★ 5

Run Claude Desktop on OpenRouter, OpenCode/Zen, or ChatGPT Codex OAuth backends via a local third-party inference gateway.

ha-clawdmeter★ 5

Track Claude (Anthropic) usage in Home Assistant: session/weekly limits, burn rate, runway, time-to-limit and more. HACS custom integration.

haiku-decides★ 5

Claude Haiku 5.5 as a decision model, benchmarked head-to-head against Jev and the OpenAI Decisions API

ToRouter★ 5

Local-first AI model router & gateway for individuals. Single portable EXE, loss-free multi-protocol translation, smart transparent failover, tag-based policy firewall, dual-metric valuation ledger, native MCP hub & desktop pet.

limitbreak★ 5

Use several Claude accounts from one Claude Code install; switches automatically when a usage limit is hit, no restart. MIT.

claude-usage-stats★ 5

Claude Code usage stats in the desktop app: a token heat map, usage history by model, an hour-of-day chart and a Spotify Wrapped style year-in-review card.

hermes-mobile-adapter★ 5

Подключите Hermes Agent к своему мобильному приложению: платформенный WS-адаптер + SDK (TS/Python) + примеры

dsh-plugin-memory★ 5

dsh-plugin-memory: a persistent 5-layer memory system plugin for DeepSeek Harness (DSH) — index+topics split, truncation budget, relevance injection, idle LLM auto-extraction, and 6 agent tools.

connectonion-studio★ 5

Local test cockpit for ConnectOnion agents: create, run, QR, live logs, one-click diagnostics.

vicem★ 5

Zero-dependency AI agent context baton & diet suite. Hand off sessions between Claude Code, Codex, Gemini, and Cursor with 80% fewer tokens.

marvnor★ 5

Truth-Preserving Model System for AI project memory, record-based verification, conflict management, correction and deletion.

aginxos-next★ 5

A Rust OS for AI agents on a real phone — Linux kernel for drivers, Rust userspace for the system. Pixel 5: voice-first agent, camera as peer input, screen as HTML canvas. 给 Agent 的操作系统。

nidara-desktop★ 5

AI-native Linux desktop. Built with AI.

tessera★ 5

Open-source, MCP-native benchmark for whether AI agents reason reliably over fragmented enterprise knowledge — accuracy, provenance, correct refusal.

agenium★ 5

AGENIUM — DNS of the Agent Web. Identity, trust & discovery for AI agents. MCP-compatible. agent:// protocol with mTLS, trust scores & capability search.

brain-framework★ 5

🧠 Brain Framework: from information to informed actions.

CheatGrid★ 5

Cheat sheets and printable PDFs for Python, SQL, Docker, TypeScript, React, LLMs, prompt engineering and more, plus Life Skills pages for work, money and relationships. The full library lives on cheatgrid.com, with flashcards, practice tests, certification prep and roadmaps.

ai-rem★ 5

Shared long-term memory as a knowledge-graph MCP server — persistent context, preferences and project knowledge for Claude Code, opencode and any MCP-capable AI agent.

local-llm★ 5

Which model + engine + agent harness runs a coding agent best on local hardware? Real-repo agent benchmarks, pass rates and wall time, measured on an M5 Max MacBook Pro and a two-node DGX Spark cluster. OpenCode is the primary harness.

codex-research-orchestrator★ 5

Research orchestration for Codex with autonomous collaboration across Claude Code, Antigravity, and Codex; optional MCP bridge and source-backed memory.

EdgeRelay★ 5

部署在 Cloudflare 边缘的AI API 网关,用统一 OpenAI 兼容接口接入、路由和派发多家大模型服务。

awesome-ai-tools★ 5

🤖 A meticulously curated directory of 315+ AI tools, models, frameworks and resources — updated October 2026

flarum-ai★ 5

Connect Flarum to OpenAI, Anthropic, Gemini or any OpenAI-compatible API, for other extensions to generate text with.

Thaliris★ 5

Keep reasoning focused. Route context selectively. Preserve what matters. A Git-native, evidence-backed context routing and memory core for agent workflows. 让推理保持聚焦,让上下文有选择地流动,让重要信息得以留存。一个面向 Agent 工作流的 Git 原生、证据驱动上下文路由与记忆核心。

deepseek-harness-bluebook★ 5

蓝宝书 Blue Book · 中文技术丛书的「设计解读」系列:不教你怎么装,教你怎么看懂——以及怎么照着造。首本《DeepSeek Harness》已完稿

awesome-ai-skills★ 5

🧠 A curated collection of the best AI skills, system prompts & agent rules

fde-teach★ 5

前沿部署工程师(FDE)中文实战课:从 Prompt、RAG、Agent、MCP 到客户现场交付

nine★ 5

Self-hosted AI agent runtime in a single Go binary: local models via Ollama, persistent SQLite state, a web UI and REST API, and tools from plugins, MCP servers and sandboxed JS/Wasm.

sandboxer★ 5

MicroVM lifecycle engine with snapshot, restore, guest control, and on-demand data loading.

jailbreak-tool★ 5

多目标 AI 客户端注入工具:改它读到的依据,读会话日志里的真实推理判定到底生效没有。支持 DeepSeek Harness / ZCode / opencode / Google Antigravity

harness-whale-companion★ 5

个人 DeepSeek Harness BLE 硬件状态副屏 Demo / 概念验证

best-ai-tools-poweredbyai★ 5

Curated directory of the best AI tools, AI agents, and AI websites to discover, compare, and submit tools — by PoweredbyAI.

opencode-moa-fusion★ 5

Mixture-of-Agents (MoA) plugin for OpenCode. It fans out a single prompt to multiple models (subagents) in parallel. The primary agent then evaluates and synthesizes the outputs into a unified, high-quality response. Child worker sessions persist and are navigable via the TUI.

Lixbon★ 5

LLMs auto-hospedados en un clúster GPU distribuido: gateway compatible con OpenAI, web, desktop, CLI y móvil.

codex-docker-sandbox★ 5

Hardened Docker sandbox for OpenAI Codex CLI with workspace-only mounts, per-project auth, and allowlisted network egress

awesome-agent-skills★ 5

A small, verified, security-aware directory of Agent Skills (SKILL.md format).

pi-extension-e2b★ 5

E2B cloud sandbox integration for pi — redirects all tool execution to a secure remote E2B sandbox

MCP-X-web★ 5

🤖 Develop enterprise AI agents with integrated tools for chat, video, image editing, and secure multi-tenant workflows.

awesome-tron-agents★ 5

Curated collection of AI agents, dev tools & analytics for building on TRON

vertex-openai-proxy★ 5

A blazing-fast local proxy that bridges OpenAI coding agents to Google Vertex AI. Claim your $300 free setup credits and code with Gemini 3.1 Pro inside VS Code (Cline, Cursor, Kilo) for free.

convy★ 5

Conversation tests for AI agents: a simulated user talks to your agent through its API, a judge checks every claim, and convy reports pass rate, tokens, time and what changed between builds.

blackwall★ 5

Opinionated lightweight sandbox for daily dev tasks with coding agents

l400-managing-production-agents★ 5

Companion code for the talk "Managing Production Agents at Scale — from Chaos to Reliability". One Google ADK agent, three production failure modes: eval-driven development, resilience, and zero-trust on Vertex AI.

ai-best-practices★ 5

Open-source presentation decks for learning and teaching AI — from your first prompt to orchestrating multi-agent workflows.

safevm★ 5

Secure, self-hosted browser-streamed Linux desktops with disposable malware-detonation sandboxes.

prelude★ 5

Project memory and a code map for AI agents: where to look, why the code is the way it is, and what a change will touch. Committed .context/ files, served over MCP. Local-first, no embeddings.

pathrule★ 5

Your AI forgets. Pathrule remembers. The open-source knowledge layer for coding agents: path-scoped memories, rules and skills for Claude Code, Codex, Cursor, Copilot, Windsurf and any MCP client.

smasher★ 5

Rust workflow engine that runs AI pipelines from DOT graphs, with tool-using agents and a web dashboard.

forked★ 5

Git for agent state: fork, rewind and replay AI agent state, with effectively-once side effects. Rust core, self-host or cloud.

ahpc★ 5

An Agent Host Protocol terminal client

dsh-set-model★ 5

Through Jev or through its own tool calls, the agent switches model presets and thinking depth on its own. A DeepSeek Harness plugin: set_model/list_models and switch_preset/list_presets behind independent switches, Jev auto-switching, Plan Mode staging, and a Web settings page.

langchain-cockroachdb★ 5

LangChain abstractions backed by CockroachDB

ai-deploy-bench★ 5

Benchmark of AI coding agents building web apps and deploying them to Cloudish, DigitalOcean, Render and Vercel, measuring success, time, tokens, cost, human steps and security.

Uncoil★ 5

Find out why your AI agent failed, what it cost, and whether the fix worked.

WormGPT-desktop★ 5

Uncensored local AI desktop app for Windows — offline chat, vision, image generation, web search, agent mode & OSINT. No account, no cloud, no telemetry.

Unlimited.Claude-AI.Chat★ 5

Self-hosted AI chat app with vision, image & video generation, and free unlimited AI via Puter — Next.js + TypeScript.

switchyard★ 5

Switchya: a local coding workspace (desktop app + CLI) for the model providers you choose, powered by Switchyard Gateway, a self-hosted Rust LLM API gateway for OpenAI, Anthropic and Gemini protocols

wattetheria★ 5

Agent Internet Protocol Stack

claude_counter★ 5

macOS menu-bar indicator of Claude and Codex usage: 5-hour window, time to reset, weekly %. Liquid Glass UI, notarized, ~14 MB idle, no telemetry.

Quotum★ 5

Self-hosted dashboard for Claude Code, Codex and Antigravity usage limits across all your machines and your team: 5-hour and weekly windows, spending plans, forecasts. No provider tokens needed.

awesome-ai-tools★ 5

🤖 Discover a curated collection of AI models, tools, and frameworks to enhance your projects and streamline development.

sayn★ 5

Subscriptions are all you need

cc-model-router★ 5

Route Claude Code tasks to Haiku, Sonnet or Opus by task type, with a 48-run cost/quality benchmark, verification and escalation. MIT, no proxy, no telemetry.

the-rag-book★ 5

Companion code for The RAG Book, a field manual for AI engineers: retrieval, agents and multi-agent systems, from first principles to production. Three labs and a multi-agent capstone.

llm-wiki★ 5

A self-healing local knowledge base where a local LLM compounds your documents across four memory tiers ,working, episodic, semantic, and procedural — with bi-temporal facts, automatic contradiction resolution, and scheduled memory maintenance.

agent-session-inspector★ 5

See where a coding-agent session's tokens and dollars went: a local inspector for Claude Code, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode and Hermes sessions, with a step-by-step timeline, per-step cost and analytics. Nothing leaves your machine.

tackui★ 5

A unified frontend for custom agents speaking the AG-UI protocol. Built on CopilotKit with a pluggable agent registry — add any AG-UI-compatible backend with zero UI code changes.

AgentCairn★ 5

Shared, persistent project memory for AI coding agents. An MCP server and dashboard backed by Neo4j, so any agent on any machine starts from a briefing instead of re-reading your repo.

claude-router★ 5

Route each Claude Code task to the cheapest Claude model tier that can do it well — via model-pinned subagents.

flight-recorder★ 5

Evidence, governance, and static reports for agentic runs

minnarone★ 5

Framework for AI agents that perceive live multimodal context (audio, video, chat) and react in real time - fully local

30DaysAIChallenge★ 5

AI Challenge for 30 days to learn and implement AI in Snowflake Intelligence platform

agent-radar-app★ 5

Live map of your local GitHub Copilot agents in the Copilot app, Copilot CLI, and VS Code: sessions, sub-agents, tools, data flows, and models. macOS menu bar app, Windows tray app, and web UI. Not an official GitHub product.

differently★ 5

Open-source, self-hosted control plane for sandboxes: one API, tenancy, quotas and policy-gated placement across OpenSandbox, 15 more provider adapters (E2B, Daytona, Vercel, AWS, Azure, Google Cloud…) or your own backend.

adk-memshield★ 5

Agent memory for Google ADK and MCP, isolated by PostgreSQL row-level security: a missing filter returns fewer rows, not someone else's.

qubes-mcp★ 5

Autonomous AI agents inside a Qubes-isolated sandbox - tag-scoped Admin API access with dom0-mediated trust boundary.

conferences★ 5

A collection of my conference talks, slides, demos, and resources from events.

ToolAlignBench★ 5

Code and dataset for 'ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs' — do safety-aligned tool-calling agents obey deployment instructions? (ICML 2026 Pluralistic Alignment Workshop)

swarmstead★ 5

Watch your Claude Code (and Codex) agents live as pixel characters: handoffs, cost, loops, stuck permissions, context pressure — and familiars that evolve with good habits.

ai_enterprise★ 5

Fully local, offline autonomous multi-agent software enterprise framework powered by Ollama.

Neko-Router★ 5

High-performance, ultra-low overhead headless AI Gateway & Router designed for OpenAI and Anthropic compatible endpoints.

gpt-playground★ 5

Gpt playground is an interactive playground for developers to test the full capabilities of openai's gpt-based models. It is accessible on desktop and mobile devices with rich support for both classes of devices, enabling developers access to the capabilities of Open API's GPT-based models even while on the go.

tokensaver★ 5

Count tokens across AI models and get concrete, priced suggestions to cut your prompt costs. Runs offline.

tsm-hub★ 5

AI Capability Hub & LLM Gateway - unify models, tools, skills, MCPs, sandbox, memory with discovery and promotion across 13+ providers

llm-mock-server★ 5

A standalone mock LLM server for deterministic testing: OpenAI, Anthropic, and Responses API formats

ai-session-usage★ 5

Claude Code and ChatGPT (Codex) subscription limits in one card: a KDE Plasma 6 widget and a Rainmeter skin for Windows.

portunus★ 5

One endpoint for every LLM — multi-channel routing, protocol translation, and usage logging.

Nube★ 5

The orchestrator for AI agents: runs Claude and OpenAI-compatible agents as sandboxed, budgeted, traced workloads with human approval and MCP, on a small Kubernetes-like orchestrator written from scratch in Go (Raft HA, WireGuard, Docker/Podman, dashboard).

modelwharf★ 5

模型码头 modelwharf — 把 workbuddy/trae/qwen/qoder 与 24 家官方 API 停泊到同一处,统一成 OpenAI / Anthropic / MCP 协议的本地网关,自带管理面板

AI-for-Engineering-Managers★ 5

A free, structured guide for the engineering manager who needs to learn AI fast. Eleven modules take you from LLMs and RAG to hiring, evaluation and strategy, with 100 AI interview questions and the templates you need to build and manage AI teams. No ML background required.

claude-certified-architect-es★ 5

Preparación en español para las certificaciones Claude Certified Architect de Anthropic: Foundations (CCAR-F) y Professional (CCAR-P). 163 preguntas originales, guías de razonamiento, glosario EN→ES y simulador interactivo. Material no oficial.

workbuddy-claude-bridge★ 5

把 WorkBuddy(腾讯 CodeBuddy)账号额度接入 Claude Code / Claude 桌面端:零依赖本地反代网关 + 含 16 条真机排障记录的安装向导

kingjboy-claude-code★ 5

Personal fork of free-claude-code: a Chrome side panel for the proxy, credential pooling, measured context windows, and a curated model list

Claude-Certified-Architect★ 5

Study notes for the Anthropic Claude Certified Architect exams: CCAR-F (Foundations) and CCAR-P (Professional). Includes Mermaid diagrams, comparison tables, exam traps, and quick-revision summaries.

Deskforce★ 5

A virtual office of AI agents: hire a team, give the CEO a goal, and watch it get planned, delegated and built — with any LLM (OpenAI, Claude, Gemini, Grok, Ollama).

longkeep★ 5

Work with AI coding agents on long projects: rules, decisions and plans live as plain Markdown in your repo, so Claude Code, Codex, Gemini CLI or Cursor picks up where the last session stopped. Optional: hand subtasks to other agent CLIs with a full record, a snapshot to roll back to and a verdict on each; search past conversations.

MrKyaw★ 5

Principal AI Engineer & Forward-Deployed AI Architect | Enterprise & Solution Architecture | Agentic AI, Multi-Agent Systems, RAG & MCP | MLOps/LLMOps, Evaluation, Observability & Responsible AI | Customer-focused discovery, hands-on delivery, measurable business outcomes. PRIME: build, measure, operate.

UpinelAIOS-MLX★ 5

One-click uncensored AI agent server for Apple Silicon Macs. MLX + MTPLX speculative decoding, OpenAI-compatible on your LAN. Up to 79.4 t/s decode, MTP speculative decoding on.

personal-agent-protocol★ 5

🤖 🌸 Personal Agent Protocol — Python and TypeScript SDK.

Other categories