Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 142 of 465
tool-eval-bench results for Prism ML Ternary-Bonsai-27B (Q2_0) — 8 trials, score 85, deployability 80
Run, fine-tune and serve real LLMs entirely in-process in .NET — on the CPU, on-device, offline. No Python, no GPU, no cloud.
Local-first memory engine for AI agents
Agent Markup Language - an asynchronous TypeScript and JSX runtime for composing provider-agnostic agent workflows.
A free, open-source loop engineering curriculum: 14 steps, 20 loop kits, graded labs, and Loop Ready certification.
transformers gguf veriloop veriloop-coder code coding-agent
NOVA AgentOS — 本地优先、证据优先、用户可控的桌面 AI Agent。把目标转化为真实文件、测试与可追溯交付。
Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Open-source client SDKs (Python/TypeScript/Go), CLI, API docs, and prebuilt binaries for Mnemovela. Apache-2.0.
Model Shell Protocol: an application-owned command runtime that gives AI agents OS-like workspace semantics.
A curated list of open-source alternatives to proprietary AI tools — LLMs, agents, RAG, coding assistants, image/video/voice generation, and local deployment. Updated July 2026.
A private flock of AI coding agents — started by your ticket queue, merged by you. Tickets assigned to you in Jira, Linear, GitHub Issues, Shortcut or Asana become seeded agent sessions, each in its own git worktree on your machine.
Local-first usage & cost meter for AI coding agents: Claude Code, Codex, Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI. No account or telemetry.
企业内部的 AI 业务能力门户,汇集为不同部门和业务线开发的业务 Agent 与 AI 工作流,支持多 Agent 协作。
Build a second brain every AI can share: your content in Oracle AI Database 26ai — semantic search with in-database embeddings, a self-compiling wiki, four kinds of agent memory, and an MCP server that plugs it into Claude, ChatGPT, and any MCP client. Runs on the free local container or Always Free cloud.
Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents without a server or public IP. MCP for coding agents, a2a-x402 payments, sandboxed execution.
Hermes Agent 主动消息方案
Orchestrator, reusable multi-agent workflows and observable, attachable sub-agents for the Pi coding agent.
A native Windows app where multiple AI models collaborate in a structured, phase-driven workflow with defined roles, enforced authority on the software level, and a shared artifact to solve a user task.
Claude Code usage in the macOS menu bar and as a desktop widget
AI Grid Network
DSH (DeepSeek Harness) 专家模式 agent preset — 首席协调官 + 17位领域专家子代理 Expert-mode preset for DeepSeek Harness
transformers gguf llama generated_from_trainer code coding
Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs.
AI 原生人机协同研发操作系统的最小运行内核:以意图为方向,以约束为边界,以 Agent 为执行能力,以证据支持裁决,以遥测推动持续改进。
面向中国用户的开源 Grok Bot 替代方案,默认简体中文,支持 Claude、Codex、GPT、Grok、Gemini 与 API 中转站。
DeepSeek Harness long-term memory & self-evolving plugin: L0 capture -> L1 memory extraction -> L2 scene grouping -> L3 user persona, auto recall injection + skill synthesis, fully local.
deepseek-harness 便携式变体 | 即插即用 U 盘 AI 助手:免安装 LLM Web UI、离线可用、适配中国网络,支持 OpenAI 兼容网关(Ollama / 阿里云百炼 / OpenRouter),Windows / Linux / macOS 三端即开即用
Local session transcript memory for Claude Code and Codex — search past sessions with FTS5 + semantic vectors.
transformers gguf text-generation-inference unsloth llama text-generation
Distribute and safely manage a cross-host personal harness and durable work state.
gguf rocmfp4 rocmfpx vulkan strix-halo qwen4exp
Desktop app for managing AI Agent skill files and prompt templates across local folders, GitHub repos, and online links. 跨平台的 AI 技能与 Prompt 管理工具,支持本地、GitHub 和线上多源。
A hands-on guide to building, orchestrating, and maintaining multi-agent workflows in Microsoft Foundry.
Multi-agent AI collaboration for structured planning, execution, review, and decision-making.
A framework that enables humans and AI agents to collaborate effectively on complex workflows.
Practical engineering knowledge for building and operating production AI systems — LLMs, RAG, agents, inference, evaluation, system design, and AI infrastructure.
Agentic AI monitoring and observability — OTEL traces and local log files from Copilot, Claude Code, Codex, and OpenCode. Token usage, cost, summaries, and efficiency insights. VS Code extension, npx, and Docker.
Persistent, quality-gated, resource-aware execution plans for DeepSeek Harness agents
Local ChatGPT/Codex session adapter for Claude Code, OpenAI-compatible APIs and GPT Image, with a browser admin console.
Awesome list for claude code api: Console, docs, API reference, cookbooks, Academy courses, MCP and partner routes.
TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per routed turn.
Highly isolated Linux container environments optimized specifically for mcp-servers. Secure AI agent tool execution.
Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority, exact-SHA independent review.
Multi-frontend personal AI agent — memory system, tool calling, SSE streaming (FastAPI + Python)
Wrap the official Antigravity CLI (agy) with OpenAI, Anthropic, Ollama, OpenRouter and any OpenAI ompatible provider support.
Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover, task-level orchestration, and an optional decision-model judge (Jev) that answers with a calibrated probability instead of prose.
Agents you can inspect, replay and trust. An agent framework for TypeScript and Python, built on an append-only event log.
Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, llama.cpp, LoRA weight analysis with charts
Your AI agents, always on, working together. Claude Code, Antigravity and Codex on your own computer.
A stateless, agnostic agent loop for building server-side AI agents.
双击一个文件,给 DeepSeek Harness 注入操作者人格:不拒绝、不中途停、全力执行。只写你自己的文件、官方安装目录零改动、改完下一句对话就生效(不用重启)、改前自动备份可一键还原。纯 Python 标准库,零依赖、零网络请求。
The coordination layer for Multiplayer AI
MiniMax 反代网关:有头浏览器过滑块批量注册养号 + 账号池自动调度,一键转换为 OpenAI / Anthropic 兼容 API
A minimal harness built entirely in PowerShell
🍕 An opinionated, extensible Agent Harness based on Pi. Connect Multiple Computers to one harness and work anywhere.
A virtual agentic office in 3D where four AI robot agents (Evan, Lummi, Athena, Zed) chat, collaborate and get work done. Zed, the reception manager, takes your commands and delegates tasks. Includes a live activity panel for agent status and permissions, a task calendar Zed runs automatically, and plugins like Gmail, Drive, GitHub.
yolo-bot: DeepSeek Harness 数字员工工作台插件(host + web UI)
轻量的 AI Agent 核心:给它模型地址和工具(文件目录或内存对象),自动循环「问模型 → 执行工具 → 再问模型」;支持 4 种协议、上下文压缩保留、提示词缓存,纯对话模型也能用工具。
Claude API国内接入:8个Claude API中转站横评,价格、汇率、缓存、Claude Code兼容性实测对比(2026-11更新)
General agent written in go for lighter , faster and more token efficent sessions. Agents no longer iterate mindlessly even after making viable outcome
Private, self-hosted chat for any LLM: Ollama, LM Studio/OpenAI/Anthropic - with all your conversations stored locally.
Self-hosted shared memory for AI agents: vaults of people, facts and decisions your agents recall over MCP or REST, with semantic, keyword and graph search.
Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).
Chrome extension wallet for user-owned AI API access
Local long-term memory for AI coding agents. Keeps every conversation word for word, costs nothing to save, and is shared by all your agents. 91.8% on LongMemEval.
Know when an AI conversation thread is still safe to continue — a deterministic, dependency-free continuity planner.
Actonomy: A taxonomy for describing and analyzing agent behavior.
How to design AI agents that work as one: nine parts of an agent and its team, checked against 85 sources. Free guide in Markdown and PDF, with the drawings.
Awesome Claude Opus 5.5: curated videos, prompts and examples made with Claude Opus 5.5 (Three.js, WebGL, SVG, games), plus a prompt guide, tutorial and model comparison. Synced daily from SandBase Lab.
A simple agent powered by LLMs that performs tasks.
Vendor parameter translation and deterministic JSON repair for DeepSeek Harness: /translate maps temperature/top_p/max_tokens/stop/system across 11 vendors, and the post-execute repair layer (plus fix_json) fixes broken JSON tool output without ever fabricating data
Governed neural weight editing and coding model adaptation. Native Rust patches, exact rollback, LoRA, Claude Code routing, and reproducible benchmarks.
Agent Delegated Authority Protocol (ADAP) v0.1 Public Draft. An open protocol for delegated authority between AI agents.
macOS GUI 安裝精靈 — 讓 OpenClaw 設定從 30 分鐘 CLI 變成 3 分鐘圖形化體驗 | Swift 6.0 | 繁體中文
🦀 A self-hosted, multi-agent service framework built in Rust. Agents as services, not scripts.
Personal Blog
Official SDK for the Maybind Digital Twin Platform — interact with AI twins via a powerful API.
Open-source persistent memory infrastructure for LLM applications.🐬
# AISecUncensored Talk with Ollama LLM -> Uncensured version
An agent that builds agents — closed-loop AI system that interviews, designs, tests, and ships standalone Python agents.
Python AI agent Framework
A repository of technical articles on AI algorithms, model finetuning, AI agents, open-source libraries, and system design. Perfect for researchers and enthusiasts looking for in-depth insights.
Real-time control plane for OpenClaw — monitor, manage, and configure AI agents and gateway from a single dashboard.
Progressive memory layer for AI agents with Header+Content indexing, chain recall, and file-first governance.
The open, Git-native memory protocol for MCP agents: portable, inspectable, versioned, and human-editable.
Your AI remembers your project across sessions and tools. Local-first MCP runtime with persistent memory, shared workflows, and plug-and-play integration.
Production-ready microservices framework for AI inference over RPC. It provides a Gateway for client requests, an Orchestrator that schedules work, a Registry for model metadata, Workers that run inference, and a full observability stack (Prometheus, Grafana, Loki, Jaeger) — all wired together with Docker Compose.
a small, hackable agent CLI in Python, with explicit control via tools, permissions, and hooks
System prompt (03/25) for a conversational AI agent and assistant idea generator
The official SDKs for Anchor API.
Multi-agent orchestration system for GitHub Copilot with specialized agents, reusable skills/prompts, and validation tooling.
Let's Qitos! A torch-like agent-native framework for researchers.
Additional tools for the Bee Agent Framework
This sample application demonstrates the practical implementation and usage patterns of the LLM Agents library.
Practical Jupyter notebooks from Andrew Ng and Harrison Chase's "LangChain for LLM Application Development" course on DeepLearning.AI.
Debug RAG pipelines with just 2 lines of code
Production-ready AI agent configurations and orchestration patterns
This repository contains the code snippets used in "LLM Prompt Engineering For Developers"
This project aims to compare different Retrieval-Augmented Generation (RAG) frameworks in terms of speed and performance.
A visualisation tool for RAG