Category

Agent frameworks & infrastructure

46,465 agents

Every agent in Agent frameworks & infrastructure, page 144 of 465

Awesome-AI-Engineering★ 14

A full-stack AI engineering playbook — infrastructure, model lifecycle, agents, MCP, memory, evaluation, and production systems.

thalamus★ 14

Use your Cursor subscription to power Claude Code — smart proxy with lazy tool loading, auto-continuation & model fallback

memory-cloud★ 14

Adaptive memory for AI agents & teams — beyond RAG. Self-hosted MCP server that gets smarter every time you search: hybrid search + a neural memory graph that learns. Works with Claude, ChatGPT & any MCP client.

gen-ai-beginner-projects★ 14

Hands-on beginner-friendly Generative AI projects covering Prompt Engineering, LLM APIs, Embeddings, RAG, Vector Databases, and AI Agents. Learn Gen AI by building real-world projects.

sema★ 14

Sema is a content-addressed vocabulary for AI agents. Precise thinking, reliable references, safe multi-agent coordination. Hash the meaning, get the word.

agent-blackboard★ 14

Multi-agent coordination system for software engineering with 9 specialized AI agents - Documentation, API Design, Backend Architecture, Java/Go Development, DDD, and Observability

ccstats★ 14

Local-first CLI (and desktop) for token and cost analytics across AI coding agents

42★ 14

42 Luxembourg — Piscine and Common Core. C, Python (LLM / RAG / information-retrieval branch), Go networking, Docker infrastructure, systems programming and concurrency.

pi-ollama★ 14

First-class local model support for pi through Ollama — reliable tools, context management, thinking controls, vision, warm-up, and telemetry.

awesome-ai-agent-frameworks★ 14

🤖 AI Agent Framework Guide (中文) | Scion · AutoGen · CrewAI · LangGraph · MetaGPT · Dify · Coze — 深度对比 + 选型决策树 | Chinese developer guide for choosing the right multi-agent framework

DovePaw★ 14

Personal AI agent orchestration runtime for Claude Code: build, schedule, and run private TypeScript agents with A2A, launchd, and an Electron UI.

pi-xai★ 14

Pi extension for SpaceXAI Grok/X.com Subscriptions

LAZYANTIGRAVITY★ 14

Open-source agent orchestration framework providing deterministic multi-agent workflows, AST verification gates, and maintainer automation pipelines.

chimera★ 14

single-executable / library which combines llama.cpp, whisper.cpp, and stable-diffusion.cpp

Midas★ 14

Local-first, eval-first memory for long-horizon AI agents — no LLM at ingest. Python SDK + MCP server with source-traceable recall, belief revision, selective forgetting, and reproducible benchmarks.

Hermes-House★ 14

🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve

switch-plus-plus★ 14

Agent Switch: Claude Code, Claude Desktop, Codex CLI, Codex Desktop, Hermes, OpenCode, OpenClaw and AI agent config switcher, model router, and local OpenAI/Anthropic gateway

evolving-agent-harnesses★ 14

Evolving agent harnesses: a research program on how far N orchestrated calls of a small model can rival a frontier model. We evolve the harness (structure + prompts) with reflective optimizers + a verified-acceptance gate.

claude-fable-5-prompt-optimizer★ 14

Prompt optimizer for Claude Fable 5, built as a claude.ai Project — 43 source-backed rules, complexity routing, and API parameter recommendations, grounded exclusively in official Anthropic documentation.

SecondBrain★ 14

A persistent MCP memory layer for AI agents. Store knowledge across sessions, retrieve it semantically, and connect any MCP-compatible agent.

deepclaw★ 14

DeepClaw——开箱可用的企业级智能体工作台及脚手架

goa-ai★ 14

Design-first agentic systems in Go: declare agents, tools, MCP servers, policies, and structured model output in Goa, then generate the durable runtime.

open-bridge★ 14

Stop re-explaining your work to your coding agent. Plain markdown and YAML in git, read at session start by Claude Code, Codex and Copilot CLI. MIT.

genai-starter-pack★ 14

Curated catalog and dataset of 50 cloneable GenAI apps and Hugging Face Spaces across RAG, AI agents, LangGraph, MCP, and more

context-summary★ 14

A Claude.ai Personal Skill that generates a structured, seven-block session handoff so you can continue work in a new conversation without losing context, rediscovering decisions, or re-explaining your project state.

shapecraft★ 14

Structured output generation for LLMs in Node.js — token-level constraints for local models, native JSON modes for cloud APIs

muster★ 14

The AI agent harness you can audit: token-waste ledger, leak-proof scoped memory, eval-gated learning, 20+ LLM providers (Claude, OpenAI, Ollama, Grok, Kimi). TypeScript, MIT.

kimi-K2.7★ 14

Kimi K2.7 Swarm Workstation — 300-agent parallel AI hive. Beats Claude Opus 4.8 on tool use (81.1% MCPMark), 5× cheaper. Win/Mac, one-click.

Memories★ 14

A macOS app to browse and manage the memory files Claude Code keeps for your projects.

AgentHub★ 14

IM-native multi-agent collaboration platform — @mention Claude Code, Codex, OpenCode like teammates

agentling★ 14

A tiny async tool-calling agent framework

api-log★ 14

Transparent LLM gateway trace recorder · sub2api / CLIProxyAPI / new-api 的 LLM 网关流量录制器

ghcp-advanced★ 14

Advanced GitHub Copilot tutorial focused on advanced concepts, Inspired by and based on the GitHub Copilot HoL by @Philess (https://github.com/Philess/GHCopilotHoL).

awesome-agent-infrastructure★ 14

A curated list of AI agent infrastructure: memory stores, vector databases, execution sandboxes, MCP servers, tool registries, observability, and evaluation tools for building and running autonomous agents.

hf-llm-api★ 14

docker region:us

GPU_memory_calculator_LLMTraining★ 14

gradio region:us

llm-race-to-the-top★ 14

gradio region:us

first-llm-classifier★ 14

docker jupyterlab region:us

LLM-Beer-Distribution-Game-public★ 14

gradio region:us

GPT-J-6B★ 14

gradio region:us

Open_gpt4O_fast★ 14

gradio region:us

Agents-A1-F16-GGUF★ 14

gguf moe vlm vision agentic text-generation

Phi-3-mini-128k-instruct-function-calling★ 14

transformers safetensors phi3 text-generation nlp code

TinyLlama-1.1B-Chat-v1.0-GPTQ★ 14

transformers safetensors llama text-generation conversational en

glm-4-9b-chat-1m-hf★ 14

transformers safetensors glm text-generation chatglm conversational

Trendyol-LLM-7b-chat-v0.1-GGUF★ 14

transformers gguf llama text-generation trendyol llama-2

DeepSeek-Coder-V2-Lite-Instruct-FP8★ 14

transformers safetensors deepseek_v2 text-generation fp8 vllm

Qwen3-Coder-Next-MLX-Q9★ 14

mlx safetensors qwen3_next quantized text-generation conversational

granite-20b-code-base-8k★ 14

transformers safetensors gpt_bigcode text-generation code granite

glm-4-9b-chat-abliterated-GGUF★ 14

transformers gguf glm chatglm thudm chat

Qwen1.5-4B-Chat-GPTQ-Int4★ 14

transformers safetensors qwen2 text-generation chat conversational

hypermemory-sdk★ 14

SDK for developing apps on top of Hypermemory

glm-4-9b-chat-abliterated★ 14

transformers safetensors chatglm glm thudm chat

claude-code-reverse★ 14

A local transparent proxy for Claude Code that captures every Anthropic API call — extract the full system prompt, track token & cache usage, and analyze tool-call patterns from a CLI or live React dashboard.

zugamind★ 14

Agents answer. ZugaMind notices. A persistent cognition sidecar that wakes Claude Code, OpenClaw, Codex, or Hermes when something deserves attention — engineered Global Workspace Theory, zero dependencies.

TeamBrain★ 14

The brain is a git repo. Memories are markdown files with YAML front-matter, committed like any other file. Git history is the audit trail; pull requests are the approval gate — nothing is written to the shared brain without human review.

jooj★ 14

Java-implemented extensible AI Agent runtime — direct Anthropic protocol connection / Spring Boot 4 assembly / multi-tool collaboration / Web UI + CLI dual-mode.

pi-fusion★ 14

Pi extension for parallel panel review and judge synthesis

federaide★ 14

P2P multi agent orchestration harness, universal automation system and IDE

pxpipe-windows★ 14

Windows fork of pxpipe: transparent Fable 5 compression for Claude Desktop on Windows 11.

flutter_ai★ 14

The complete AI chat toolkit for Flutter — streaming, tools, generative UI, voice, and a batteries-included UI kit. Provider-agnostic (OpenAI, Anthropic, Gemini), state-manager-agnostic. The Flutter answer to Vercel's AI SDK + AI Elements.

aleph★ 14

A science inference cluster — every model, from protein folding to LLMs, behind one OpenAI/Anthropic-compatible endpoint and a single key. Built to run beside HPC so agentic AI researchers can drive simulations and model inference together. Self-deploying on RKE2 with KServe/Knative + HAMi GPU.

xuanji★ 14

璇玑 Xuanji —— Go 单二进制 AI 网关,OpenAI / Anthropic 双协议汇聚。one-api / new-api / LiteLLM 轻量替代品,自动分流、负载、重试,成本优先路由,高可用不中断。

ZeroMem★ 14

Zero-token long-term memory for Claude Code. Indexes your own session transcripts and retrieves evidence deterministically — entity-context graph + temporal hierarchy, no LLM call anywhere in the memory pipeline. It tells you when it does not know.

a2acode★ 14

Serve any ACP coding agent — Claude Code, Codex, opencode — over the A2A protocol, with tool progress, file diffs, and permission prompts preserved.

AcruxCore★ 14

Open-source LLMOps platform with prompt management, an OpenAI-compatible AI gateway, OpenTelemetry tracing, a versioned tool catalog, and LLM evaluation. Use hosted or self-host with TypeScript and Python SDKs.

dotnet-coder-14b★ 14

transformers safetensors gguf qwen2 text-generation csharp

mirasim-relay-bridge★ 14

把 Mirasim 内置的 Anthropic 反代成API直接调用

llm-engineering-lab★ 14

A practical Generative AI engineering lab exploring LLM foundations, tokenization, deployment strategies, and real-world AI system design.

ragleap-core★ 14

Production-ready AI Business OS — 46 autonomous AI Employees, Graph RAG (Neo4j), multi-channel, BYOK across 17 LLM providers plus custom/local endpoints (Ollama), automatic fallback. 8 libs (Python+Java). Self-hosted, MIT licensed, guardrailed autonomy for regulated industries.

KAT-Coder-V2.5-Dev-MTP-APEX-GGUF★ 14

gguf safetensors qwen3_5_moe moe apex quantized

UIGEN-FX-Agentic-32B★ 14

transformers safetensors qwen3 text-generation unsloth conversational

NexusMem★ 14

Your agent can read git log. It can't read the shell commands you tried that failed. NexusMem indexes shell history with exit codes, git commits and diffs, and project docs into a local SQLite database, and serves back a token-budgeted slice on demand. No cloud, no account.

hr_agentic_chatbot★ 14

Agentic chatbot built using a chainlit interface

agentkot★ 14

The best AI harness you can run yourself. One file: web UI, tools, memory and orchestration built in. Run a team of agents across providers at once - lead on Claude, architect on GPT, researchers on DeepSeek. No sandbox, no skills, no MCP: a tool, not a nanny.

leviath★ 14

A structured agent runtime for LLMs. Structured context, multi-stage workflows, and ECS-based orchestration in a single binary

swarm★ 14

Local-first control plane for AI-agent development — watch every Claude Code session live, ledger tasks/worktrees/resources, track token spend and cost, enforce rules.

angelus★ 14

Local-first control plane for long-running and multi-agent AI systems. Observe, steer, recover and orchestrate agents.

awesome-ai-system-design★ 14

800+ real-world ML & LLM system design case studies from 150+ companies Google, Meta, Netflix, Uber, Airbnb & more. Production AI, not theory.

deliberon-releases★ 14

Assemble the AI council you can't afford to hire. Deliberon — structured multi-agent AI deliberation for Windows. Installer downloads + release notes.

october-bus★ 14

Open communication and coordination for AI agents.

agimate-backend★ 14

Core of the AgiMate agent platform: per-agent access to connectors and tools, credentials that never reach the model, every call checked before it leaves and logged after

DeepSeek-Harness-Hub★ 14

🌐 DeepSeek 官方与开源生态插件市场 (deepseek.stream) 使用指南与一键安装协议规范

K2★ 14

K2 by Alakazam Labs: AI agents, chat, mail, documents and apps on a server you own. Free and MIT licensed.

langchain-sandbox-opensandbox★ 14

OpenSandbox sandbox backend for LangChain Deep Agents - run agent-generated code and file operations in an isolated OpenSandbox environment.

Qwen2.5-Coder-32B-Instruct-8bit★ 14

transformers safetensors qwen2 text-generation code codeqwen

muteval★ 14

Mutation testing for your LLM evals — degrade the system under test and check whether your evals would actually catch a regression.

Noval★ 14

A provider-neutral execution kernel for strong-model, thin-harness agents.

Caravan★ 14

A long-horizon agent orchestration toolkit in OCaml implementing Cordis-like extensibility and graceful fallbacks

subagent-cli-skills★ 14

Skills to teach agents from different vendors call each other from CLI. Let Claude prompt Codex and Pi as Subagent.

Replete-Coder-Qwen2-1.5b-GGUF★ 14

transformers gguf text-generation-inference unsloth qwen2 text-generation

fable-method★ 14

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/grow) + adversarial eval.

pi-mesh★ 14

Live agent-to-agent communication for Pi — local broker, mesh.v1 protocol, honest delivered/read/answered statuses, hash-only ledger. Zero runtime deps. Install: pi install npm:pi-mesh

fleet-codex★ 14

Community Codex Multi-Agent V2 arrangements: lead agents, specialist TOMLs, orchestration skills and optional hooks.

neo-agent-brain★ 14

Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identity, memory and review across labs alive between sessions — the Brain Neo.mjs runs on itself. Multi-tenant: onboarding a codebase is a config entry, not a fork.

agent-vcr★ 14

Snapshot tests for LLM tool calls — record once, catch regressions forever. Zero API cost in CI.

llm-cpp★ 14

Add ChatGPT or Claude to C++ with one file.

discussions★ 14

💬 The community space for @openapi — APIs, open source, ideas, projects and conversations.

veroroute-edge★ 14

Zero-weight AI gateway for Cloudflare Workers • Gateway de IA zero-peso para Cloudflare Workers. Multi-provider routing with auto-fallback, key pool, OpenAI+Anthropic endpoints, context compression & RAG search. One-click deploy.

cagliostro-v3.5-chat★ 14

transformers safetensors cagliostro text-generation chat conversational

Other categories