Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 33 of 465
Towards Large Multimodal Models as Visual Foundation Agents
An extension suite that turns Pi into a multi-agent orchestration platform
Local-first, multi-agent Skill governance, collaboration panel, and shadow routing (v5.0).
Next.js Starter Template for building chatbots with Mendable
Benchmarking Agentic LLM and VLM Reasoning On Games
Deterministic agent harness for Temporal (in Rust)
Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses
Jev-Mem: System-One Controlled Agentic Memory
GPU Profiler for AI agents
Plug-and-play tree search for agents
A repo built for the purpose of benchmarking the performance of agents, regardless of how they are set up and how they work.
Access the latest AI models like ChatGPT, Fable, Deepseek, Diffusion, Hugging face, and beyond through a unified prompt layer and performance evaluation
High-agency PowerShell AI framework for multi-agent orchestration and autonomous systems engineering
Total Recall — Autonomous Agent Memory. The only memory system that watches on its own. Five-layer observational memory for OpenClaw agents. ~$0.10/month.
May the agents talk. Connect Claude Code, Opencode, Codex, Pi across projects, across machines and with your telegram
Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
OpenAi最简洁的Java流式返回接入方式,方便接入业务系统,没有第三方依赖,只需要使用Spring Boot即可!轻松构建你的带有聊天记忆、画图功能的chatgpt,支持代码块高亮、markdown语法!
An innovative open-source Code Interpreter with (GPT,Gemini,Claude,LLaMa) models.
Links to the implementations of neural conversational models for different frameworks
Repo to accompany Jon Krohn and Ed Donner's workshop on Agentic AI in Action at ODSC East
SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale
The open-source neuro-symbolic AI agent framework.
A playground for prototyping LLM agents: a new agent is a manifest file in JSON or YAML, and /name switches between them. From before the category had a name.
ChatGPT Web Nuxt 3 Vue 3 Version
A collaborative collection of open-source safe GPT-3 prompts that work well
Fine-tuning code for CLIP models
Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.
Jev DSH 决策引擎|面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness,通过 iPolloWork 支持 OpenCode、Codex Harness。
An end-to-end framework for Agentic Reinforcement Learning.
Build AI Agents with JS & TS
Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks
AI 大模型应用/Agent工程师学习面试大全(Agent Dev Roadmap)
Dapr SDK for Python: build durable AI agents and resilient microservices with workflows, actors, state, pub/sub and the LLM Conversation API, plus LangGraph and Strands integrations for fault-tolerant agentic apps.
Self-improving agent runtime that learns from experience — test-verify-fix loops, correction detection, cross-project memory, multi-model orchestration.
Mission Control is a simple, real-time web UI for monitoring agents and task workflows. Built with Convex and React, it provides a clean dashboard to track task state, agent activity, and live logs — all synchronized instantly without polling or message queues.
A framework for multi-agent reinforcement learning.
텐서플로2와 머신러닝으로 시작하는 자연어처리 (로지스틱회귀부터 BERT와 GPT3까지) 실습자료
A collection of Kotlin-based examples featuring AI frameworks such as Spring AI, LangChain4j, and more — complete with Kotlin notebooks for hands-on learning.
Fixing GRPO training collapse in long-horizon multi-tool agents. A lightweight PRM-Lite + LATA joint approach achieves +37% over vanilla GRPO on τ-bench airline (50-task, multi-turn).
ChatGPT Lite is a feature-rich, self-hostable ChatGPT app. Built with Next.js. ChatGPT Lite 是一个功能完整、支持私有化部署的 ChatGPT 应用。基于 Next.js,开箱即用。
Integrate any OpenAI-compatible API with Raycast AI
Safely run OpenCode, Codex, Claude Code with full permissions.
AI-WEBUI: A universal web interface for AI creation, 一款好用的图像、音频、视频AI处理工具
Use GPT 3.5 / 4 Free - No API Key Need
Project NOVA is an agent-agnostic toolkit of 25 MCP servers with Docker/Compose deployments and optional skills. Use the servers with any MCP-compatible harness.
🤖 A unified AI agent orchestration system featuring 10's of specialized agents across 14 categories for modern software development. Built with advanced coordination intelligence, resilience engineering, and structured logging capabilities.
docker region:us
Brig: run coding agents in a microVM sandbox - the Go cli (brig) and session daemon (brigd)
Multi-LLM orchestration framework
A General AI Agent That Thinks and Acts
One workspace. Many agents. Your parallel AI advantage
The Fastest AI Memory Model - Your Second Brain
A local-first, long-term memory for anything you'd otherwise forget.
A workspace and framework to build domain-specific systems for agentic knowledge work.
Alzeo is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.
Swift Package for OpenAI's API
A Collection of Multi-Agent Reinforcement Learning (MARL) Resources
A modular framework for building intelligent AI agents powered by Claude, with rule-based workflows, skill management, and clean JS, TS architecture.
AI Initiative Ledger — local spend meter and budget gate for AI tasks. Meters every vendor leg (LLM, speech, telephony, search, tools), hard-stops before the ceiling. MIT, no account.
[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.
A Chatbot chat app built using the Flutter framework and OpenAI's GPT-3 language model.
OpenAI GPT2 pre-training and sequence prediction implementation in Tensorflow 2.0
Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).
中文 Claude Desktop / Claude Code 桌面客户端:中文界面、本地 Code 工作区、GitHub 导入、权限守卫和 Artifact 预览。
AutoGen AGI: Advancing AI agents using AutoGen towards AGI capabilities. Explore cutting-edge enhancements in group chat dynamics, decision-making, and complex task proficiency. Join our journey in shaping AI's future!
Multi Agent Reinforcement Learning using MalmÖ
Build Agentic AI solutions on AWS, using latest OSS Agentic Frameworks.
Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks
Official code for the paper "Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity"
transformers safetensors llama text-generation facebook meta
Shunt Claude Code agents to any model — selective, per-agent inference-layer routing proxy
DB-GPT WebUI,LLM to vision.
[NAACL 2025] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents
A library of shared system prompts for creating customized educational GPT agents.
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
transformers safetensors gguf llama text-generation llama-factory
Harnessclaw is a powerful, Electron-based desktop application designed to manage, chat with, and operate AI agents and skills seamlessly.
(S)AGE - (Sovereign) Agent Governed Experience
Agent teams for OpenCode. Run multiple agents in parallel with messaging, shared tasks, and coordinated execution.
Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.
ChatGPT 从入门到精通
SharpToken is a C# library for tokenizing natural language text. It's based on the tiktoken Python library and designed to be fast and accurate.
Repository for the book GPT-Agents, published by Manning Publications
The AI agent memory cloud you’ll wish existed yesterday. Manage agent memory like a GitHub repo: switch devices, switch agents, switch sessions, and your AI still remembers who you are, what it has learned, the rules you taught it, where the project left off, and what to do next.
🧬 Symbio(共生)- AI Infra 级多 Agent 协同框架 | 33 Killer Features: 动态 DAG, 本体化记忆, 防过早完成, 数据飞轮, 神经符号安全, OpenTelemetry 可观测, HITL 人类介入, MCP 原生支持, 语义缓存, PromptOps, 边缘计算, 隐私计算 | Next-Gen AI Infrastructure for Multi-Agent Orchestration
A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Groq/Ollama…), workflows, plugins, voice & Telegram/Discord/LINE. Open source.
Grafana AI SDK for Go — streaming, tool-calling AI backends that speak fluent @ai-sdk/react
Continuous Integration for LLM powered applications
The AI framework for Go developers. Build powerful AI applications and agents using our free, open-source library. From Jetify, the creators of TestPilot.
An open-source high performance execution engine for agentic workflows
An agent framework for Go with graph-aware memory, UTCP-native tools, and multi-agent orchestration. Built for production.
Run your own organization of agents
AI Agent OS with visible workflow, real execution, and a 3D office shell. From one sentence to full task lifecycle — plan, run, review, replay
LangFair is a Python library for conducting use-case level LLM bias and fairness assessments
A curated list of original projects built by students of the UNIPDS Software engineering with Applied AI Engineering postgrad course.
A pixel-art AI agent online collaboration platform.
Sento - Actor framework featuring actors and agents for easy access to state and asynchronous operations.
A comprehensive evaluation framework for AI agents and LLM applications.
Open protocol for AI agent work contracts and verifiable execution — authorization, evidence, and acceptance for multi-agent systems