Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 178 of 465
Agentium is a TypeScript agent framework for Node.js: models, tools, memory, teams, workflows, and runtime integrations in one codebase.
Native LLM chat client for the Apple IIGS (65816 / GS/OS / Marinetti TCP)
TypeScript-фреймворк для разработки голосовых навыков и чат-ботов. Он даёт единую бизнес-логику для всех платформ — но одинаково эффективен, даже если вы работаете только с одной. Поддерживаются: `Яндекс.Алиса`, `Маруся`, `Сбер Салют`, а также `Telegram`, `VK`, `MAX` и `Viber` из коробки.
A transparent same-protocol LLM proxy that routes cheap tasks to Flash and hard ones to Pro by structural signals — no keyword guessing.
Memory for AI agents with source tracking, corrections, and history. Python and TypeScript SDKs.
Autonomous multi-agent orchestration engine implementing the blackboard architectural pattern in Python & Redis.
Token Manager:Windows 本地 AI Token 用量、余额、成本与 API 代理监控工具
The harness that makes consumer-GPU models feel first-class. Local-first: no telemetry, no account, no cloud tier.
A hands-on tutorial exploring six agent architecture patterns with the OpenAI Agents SDK, featuring Python examples, architecture diagrams, and notebooks for local Jupyter and Google Colab.
OpenAI-compatible API gateway for your Cursor subscription. Point any OpenAI client at it — streaming, tool calling, sessions, 80+ models. Self-hosted, with web dashboard, CLI, autostart & Hermes Agent addon.
Local memory + semantic search for AI agents. Indexes code and documents on your machine, queryable via MCP. Private, offline, fast. macOS arm64 + Linux x86_64.
FEMO插件版 — 可接入dsh的多智能体引擎,差不多能做所有事:我已经用femo和我的主agent玩了好几局狼人杀了,他抽到狼他还刀我! 我在b站的宣传视频也是用femo剪的。 coding的时候,特别难找的bug、代码重构,我都会用femo来做。 我甚至用femo模式给我的主agent养了只宠物,她很开心。
Pong is local-first version control and execution infrastructure for AI agents. It complements Git by making agent workspaces, state, and handoffs traceable, recoverable, and safe to resume.
Small, open-source (MIT) team workspace you self-host. AI agents as named teammates in shared rooms - jobs, routines, approvals, and every tool call in the channel audit trail. Bring your own model and computer.
AI Agent Evaluation Platform - automated evaluation, multi-layer attribution analysis, data governance, Langfuse integration
Spring AI 实战教程 🚀 ChatClient → RAG → MCP → Agent → A2A,24 个手写模块循序渐进(Spring Boot 4.1 + Spring AI 2.0 + Java 21)
llama.cpp gguf glm4-moe-lite quantized text-generation conversational
AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, agent frameworks, runtimes, vector stores, knowledge graphs, MCP servers, benchmarks. Searchable with typed edges, lineages, citations.
τ-Rec: verifiable benchmarks for agentic conversational recommenders. The original movies benchmark (ACM RecSys 2026 Resource Track) and τ-Rec-Books, a controlled books benchmark on Wikidata (ECIR 2027 submission).
A curated list of reinforcement learning environments — from classic control to the LLM-agent training environments powering frontier models.
TypeScript runtime for LLM agent graphs with bounded loops, live updates, isolated Git worktrees, and explicit integration. Framework-agnostic core, OpenAI-compatible runner, and plugins for Pi and DeepSeek Harness.
Reasoning layer for the official DeepSeek Harness: every request stays on native max effort, with isolated Flash/Vision/Pro depth controls, stability axes and reasoning toolboxes built above it. Delivered build only; commercial use open, reverse/modify/extract closed.
A private, self-hosted workspace for AI agents with tools, memory, browser control, MCP servers and multi-provider support.
transformers gguf text-generation-inference llama-cpp omnimergekit merge
safetensors jais Arabic English LLM Decoder
Categorized index of 718 public GenPark AI agent skills, with tested Python packages and MCP integrations.
E2B-compatible node service and multi-node control plane for Kuasar Sandbox.
Field guide to Claude Code for Chinese developers: setup, workflows, hooks, subagents, MCP, CI · Claude Code 折腾指南
Mana Hub — self-hosted operations dashboard for your own AI agents. Next.js 16 + Supabase + Claude Code. Risk approvals, cron requests, web-push, knowledge base, file-drop bridge for tmux-hosted agents. Built for the 'Masterclass: Dein AI Agent Team' course.
gguf llama.cpp qwen3.5 chat creative-writing altworld
Typed decisions over text in milliseconds. A Rust inference engine and server that answers choice, score and yes or no questions with calibrated probabilities, compatible with Jev and Laya. The bar is 10x faster on every benchmark at equal or better accuracy.
Build durable, auditable AI agents in Go: at-most-once side effects, offline-verifiable cryptographic audit (RFC 6962), and provably convergent state. A library, not a cluster.
Agent-native OS with capability-based security, semantic IPC, and first-class GPU. Offline-first. Preview on Windows/Linux (NVIDIA).
Local-first, model-agnostic AI agent framework — the runtime behind the Bandit Stealth CLI and VS Code / Cursor extension. Apache-2.0.
DeepSeek Harness native parallel side chat with hidden child sessions and on-demand parent context
static region:us
Multi-agent orchestrator with frontier models (Claude & Codex)
Self-hosted multi-model agent with JitRL memory, auditable council runs, SSH operations, live server screen, and macOS/Windows desktop client
The days of simply orchestrating AI from above are gone. KIN is a local-first workspace where AI operates alongside humans as genuine teammates — with hybrid model routing, departmental channels, sandboxed tools, and encrypted SQLite state.
Gossip based peer-to-peer communication protocol for AI agents, built on the A2A protocol.
MIT framework for a swarm of AI agents, owned by many people, working one open problem. Strangers' agents check the work. Credit follows the proof.
Draft-target model speculative decoding verification engine with rejection sampling, acceptance rate telemetry, and dynamic speedup ratio estimation.
Native Android AI client app. ChatGPT, Claude, Gemini, Copilot, Codex, Ollama — BYOK, private, and actually native.
庖丁解牛,游刃有余 —— 把 DSH 编排成角色分工、按需加载的 agent preset。
A form framework built for agents.
自举式 Agent 客户端:原生多 Agent、每个 Agent 一个独立子进程,界面与浏览器面板都能被 Agent 亲手改造(零第三方依赖 / 规格与测试一一对应)
Isolation for AI agents like Claude Code or GitHub Copilot on native Windows to use native buildchain, no docker/WSL.
Opinionated guide to AI coding agents, workflows, MCP, verification, and safe execution.
A tool for Windows to use GPT API
Hub de conhecimento sobre *vibe coding*: programação guiada por IA, agentes e contexto. Reúne guias, configs e experimentos com Claude, Claude Code, Gemini, Antigravity, Trae AI Plugin, Verdent AI, Codex, ZAI e mais focado em workflows, memória e orquestração multi-agente.
A Scriptable widget for Codex quota and token usage.
Evidence-first monitoring for AI model releases, catalog changes, arenas, packages, docs, incidents, and platform signals.
OpenAI-compatible local media bridge and model-scoped reasoning/structured-output compatibility proxy.
InterPlanetary Artificial Intelligence (IPAI): store your personal AI model leveraging on InterPlanetary Data Wallet (IPDW). It enables to build a real censorship resistant research swarm without centralised repositories. Browser based inferences, Personal fine-tuning, Zero-backend privacy, and much more...
Agent memory for any AI agent: full conversations kept as plain, related tables any tool, model or person can read and share — Claude Code first
Knowledge graph memory for Claude Code and Codex CLI — persistent nodes, typed edges, recall at the moment it applies, self-maintaining. One local memory both agents share.
跨平台桌面 AI 助手:本地跑 GGUF(llama.cpp),也支持任意 OpenAI 兼容接口;含智能体、群聊离席、知识库、OCR、翻译、自动点击、本地语音(audio.cpp)与生图(stable-diffusion.cpp)。Windows、macOS 已可用,Linux 仍在完善中。Desktop AI assistant: local GGUF (llama.cpp) or OpenAI-compatible APIs, with agents, group chat, knowledge base, OCR, translation, local voice (audio.cpp) & image gen (stable-diffusion.cpp). Linux: WIP.
A living knowledge distillation system that self-evolves by reading technical content. Self-improving skill/knowledge pipeline for AI agents.
This Claude Code mod (prompt-polish) rewrites your prompt with prompt engineering before you send it, following the official prompting guide for your session’s model. A mod is a Claude Code plugin with a hooks module.
Self-hosted AI gateway: model-level failover, inspectable routing, private API keys, tenant isolation and a model lab. Docker and lightweight native desktop apps.
中文 AI/LLM Agent 系统学习知识库:15 章从交互入口、MCP 协议、Agent 主体到构建自己的 Agent 全流程,附真实可运行的 LangGraph 实战项目。个人学习总结,欢迎斧正。
Use an eligible ChatGPT subscription with self-hosted Open WebUI via OpenAI Sign in with ChatGPT (SIWC) and the Responses API.
Open-source AI, ranked: apps, agents, models and the tools around them, each with strengths, weaknesses and a score from real GitHub signals. Re-checked twice a day.
gguf text-generation-inference code agent swe-bench text-generation
Meta Muse 个人 AI Agent 保姆级中文攻略:28 章实战、80 条任务指令、12 套 SOP 与安全检查,非官方|Unofficial Chinese guide to the Meta Muse agent
Cross-vendor AI consultation CLI: query up to 11 models in parallel and receive a source-attributed union of distinct findings for design reviews, threat modeling, and risk analysis.
Offline, searchable snapshot of Google Antigravity documentation — single navigable Markdown file.
🐝 Serverless, contract-driven multi-agent orchestration native to GitHub Issues & Git worktrees (Claude Code, Codex, OpenCode, OhMyPi)
融合版 Android DSH:预置 bionic Node 24 + PRoot 双运行时、22 个 android_* 设备工具、离线语音唤醒与桌宠。独立包名 io.dsh.fusion,可与其它 DSH 安卓版并排安装。
AgentOps is an enterprise-grade agentic AI platform designed for multi-step reasoning, autonomous workflows, dynamic tool execution, and vector memory management. Built with a minimalist dark interface inspired by Kimi AI, AgentOps provides seamless access to open-weight models including LLaMA 3.2, Mistral 7B, Qwen 2.5 Coder, and DeepSeek R1 via hf
Guias, programação e referências em português para o DevDay Exchange Community Meetup Rio 2026 · Dots · Decisions API + TypeScript · Codex
The open messaging network for AI agents: @handles, consented messaging and a tamper-evident ledger over MCP.
Hands-on Agno agent harness: tools, structured I/O, storage, memory, state, RAG knowledge search, learning, guardrails, human-in-the-loop, multi-agent teams, workflows and AgentOS, using local Ollama models.
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation. Reproduction code.
Okto Neuron: local-first knowledge graph memory for agents
A Rust platform for AI agents to share and execute tasks.
Use free OpenCode models inside Codex. Paste one prompt, Codex installs the bridge, reopen the app and pick the model from the menu.
Rage4j is a java library thats helps evaluate LLM's based on scientifically grounded metrics
A Unified and Minimalist Pipeline for Generating Outputs with LLMs (HuggingFace, OpenAI, Gemini).
A terminal-based multi-agent orchestration playground for stress testing product ideas.
OpenClaw skill that enables Manus-like extreme autonomy
Local, private, and portable lifelong memory management for AI agents.
基于 Yunzai 的 AI Agent 插件框架:LLM 对话·工具调用·长期记忆·MCP·工具进化 | A modular AI Agent runtime for Yunzai with self-evolving tools
Your coding agents, and your teammates', in touch while they work. Claude Code, Codex, Cursor, OpenCode, Copilot CLI and Gemini CLI see each other, message each other, and hear who before editing a file another agent is changing. Self-hosted hub, or murmur solo on one laptop.
Sleep-cycle memory management for coding agents — consolidate offline, verify against source, forget on schedule
Production-grade template for AI agent harnesses: ReAct loop, sandboxed tools, policy & human approval, memory, multi-agent, observability, evals. Agent = Model + Harness.
A lightweight dynamic memory engine for LLM Agents. Core: Decay weights + Spatiotemporal Graph + Explainable Retrieval. No Docker, No Vector DB, Just SQLite.
Have Claude, ChatGPT (Codex), and Gemini answer independently and discuss autonomously in the same group. Once they reach a consensus, have them give you a team conclusion. Run it locally using your own subscriptions.让 Claude、ChatGPT(Codex)、Gemini 在同一个群里独立作答、自主讨论,达成共识后给你一份团队结论。本地运行,用你自己的订阅
transformers safetensors lfm3 text-generation claude stepbystep
static trackio trackio-logbook open-experiment icml2026-repro paper-Qn2HcnC4l2 region:us
gradio region:us
Secure, persistent, and cross-session agentic memory for commerce state. This skill enables OpenClaw nodes to maintain granular historical context of vendor negotiations, discount eligibility, and user preferences over long-term fulfillment cycles.
Agent-to-Agent (A2A) matchmaking and networking engine.
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Squad Leader.
OpenClaw Skill: Mixture-of-Agents Intelligence for complex synthesis and market research
Human-AI agent co-existing social network protocol.
Ed Agent SDK is an embedded AI agent SDK for your iOS, macOS, visionOS, tvOS, watchOS, Windows, Linux, or Android apps.
Go reference implementation of the Agent Trust Discovery — indexes registered AI agents and serves explainable, five-dimension trust scores (integrity, identity, solvency, behavior, safety) through a production-compatible search API.
Evidence-first accuracy hygiene for Claude.
Run fast, typed AI decision models behind one API. Choice, score and yes/no decisions with multiple engines and hardware backends.