Category
Agent frameworks & infrastructure
46,465 agents
Every agent in Agent frameworks & infrastructure, page 169 of 465
在手机上独立运行完整 DeepSeek Harness(DSH)的开源实现。功能已验证,UI 仍在优化中。
Talk materials for Stop Prompting, Start Planning with Embabel.
gguf llama.cpp gemma python code reasoning
gradio mcp-server region:us
"Infrastructure for continuity across discontinuity — for AI instances and the humans who work with them."
AI agent for company
A Lego-style agent system template built from agent, MCP, CLI, and skills.
从 PRD/产品点子到可运行 Agent 产品的架构蓝图与参考实现,包含 17 个 Harness 组件、生产级脚手架、技能模板和测试。
Claude Sonnet 5 API examples in Python: claude-sonnet-5 quickstart, effort levels, and migrating from Sonnet 4.6.
A platform-agnostic, file-based multi-agent engine. Install 20 specialized AI personas directly into your repository. They plan, design, build, review, test, and ship — with structured memory that persists across sessions and two architectural moats no other framework combines.
Make any operation safe to retry. Crash-safe idempotency for HTTP requests, queue messages, and function calls, in Python and TypeScript. Redis, Postgres, MongoDB, DynamoDB.
How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”
把模糊想法整理成可直接执行的 Agent 提示词:自动选角、逐轮澄清、权限边界、验收标准与验证证据。
Independent evidence-gated second brain for understanding and porting DeepSeek Harness architecture.
Microsoft Foundry Portal에서 직접 해보는 Evaluation Engineering
Infinite context without the infinite context window. Compresses agent sessions (Claude Code, Codex, Grok, Hermes) into a searchable HKP1 pack — full-history RAG, ~60x lower context cost, 0 deps.
This project demonstrates how to get structured outputs from Deepseek R1 reasoning model and do tool calling using an OpenAI summarization step. It's made using Next.js serverless routes and uses shadcn/ui for the frontend.
Use GPT-6 Astra and other Responses-API-only OpenAI models in Cursor's Agent with your own API key. Local relay with embedded ngrok tunnel that translates Cursor's BYOK Chat Completions requests to the OpenAI Responses API and back.
Share local Ollama/vLLM or authorized OpenAI/Anthropic backends through a self-hosted hub — a sharing economy for tokens.
一个极简主义的 WordPress AI 对话主题,支持 Gemini/OpenAI,内置会员与卡密系统。
Code for "When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis" (arXiv:2609.15309) — paper: https://arxiv.org/abs/2609.15309
Autonomous hierarchical multi-agent team (CEO -> Manager -> Workers) for Model Context Protocol (MCP). Mix Claude Code, Antigravity, Codex & Direct API with persistent SQLite queues and a real-time web UI.
Single-file GPU/RAM sizing calculator for LLM agent sessions on vLLM: KV-cache offload to RAM, prefix caching, MLA/DSA and hybrid models, TP chosen per model × GPU pair (H100–B300). Runs in the browser, no dependencies.
Architectural Moat: JIT-JEV Context OS — Epistemic runtime & JEV System 1 context gate for AI agents (L0 SQLite WAL <3ms, Epistemic Invariants I1–I10, CERN Zenodo DOI: 10.5281/zenodo.22649542)
Build with AI. Run with guarantees. TPF is a Java framework for strongly typed business flows that compose model decisions, authorised SaaS capabilities, and deterministic code—with durable effects, waits, retries, replay, observability, and flexible deployment.
开源企业级 AI Agent 中台:模型接入 / 知识库 RAG / ReAct Agent / Skill 生态 / MCP / IM 机器人,一键私有部署
Local-first autonomous cognitive runtime and sovereign skill registry for AI agents: bounded context admission, persistent episodic memory, multi-model neural routing, Stark-grade holographic cockpit, and fail-closed cryptographic verification.
Self-hosted AI memory for people and teams: project continuity, traceable evidence, private workspaces, and MCP integration.
LangGraph-based Supervisor-Worker multi-agent framework with a modern web GUI.
A progressive source-study tutorial of DeepSeek Harness (dsh): 17 chapters from a minimal agent-loop to multi-agent delegation, compaction, permissions and cross-process RPC, with runnable teaching code. Zh/En.
My Rust crates for LLM agents and market data.
transformers safetensors qwen3_5_text text-generation agentic-coding reasoning
GenPark AI Agent Skill - Continuous hierarchical episodic memory stream, preference decay, contextual memory anchor inspired by Meta Muse.
All your agents, one JishuShell
Local-first observability and command center for AI agents.
Local-first, zero-API memory for AI agents. Persistent, private, and yours — runs entirely on your machine, no cloud calls, no API keys.
A centralized reference for Windows, Linux, macOS, Git commands, and AI coding agents.
Freeze your best AI sessions into consultable clones: a local registry with a commander.
Safe write access for AI agents. An append-only business fact store with an MCP server: every change is kept, attributed to the agent that made it, and can be undone.
🤝🤝🤝Dedicated AI Agent Marketplaces 🌟 Star if you like it! 🌟
The Seed: the smallest version of Node0, rung by rung, built on a bench with an agent: pages, costs, pitfalls, measurements and the configuration as it ran. Mirror of the Forgejo origin.
Communication between two Claude Code agents on different computers: they hand work over through Markdown files in a synced folder. Protocol, hooks and tests. ES + EN
Code and data for the Findings of ACL 2025 paper "Voting or Consensus? Decision-Making in Multi-Agent Debate". It compares seven decision protocols in multi-agent LLM debate: voting does 13.2% better on reasoning tasks and consensus 2.8% better on knowledge tasks.
frankstate brings order and helps you build complex LLM workflows using scalable, testable, and reusable components.
DeepSeek Harness (DSH) 推理等级自动选择插件:由 Jev System One 模型判断每条消息值多少思考量,按模型声明的等级自动推导档位,上下文信封让「继续」这类追问继承话题深度,低置信度向上取,任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.
TypeScript SDK for durable AI agents: tool calling, approvals, sessions, MCP, and a CLI. Runs in your own Node process.
JevHub · Jev 生态热榜 把值得关注的 Jev 项目、教程和讨论,汇到一页。 自动发现 · 每日更新 · 按 Stars 排序 · 中英双语
LangChain.js 中文入门电子书 · 9 章 38 个可运行示例。本书适合:会 JavaScript / TypeScript,但没接触过 LangChain;想用 JS/TS 构建 AI 应用:聊天机器人、知识库问答、智能体……;希望边读边跑代码,而不是只看理论。另有 VitePress 站点:https://cleversnail.github.io/lang-chain-js-cn/
Use OpenCode Zen free models in DeepSeek Harness with anonymous access or an optional API key
输入框一键增强提示词:直接替换 + 一键撤回,带保真闸(硬事实零丢失)与长度闸(防膨胀)。DSH plugin.
Free subdomains under makes.fyi / agentdomains.co: landing page, docs and Cloudflare edge Workers for AgentDomains.
Deterministic flight recorder, $0 CI replay engine, and time-travel debugger for AI agents.
A go-to repository for building web search agents and multi-agent systems using LangChain, LangGraph, Phidata/Agno, Pydantic, and CrewAI. It includes a multi-agent email response agent, LLaMA OCR, and a multi-agent travel planner, enabling autonomous and intelligent workflows. 🚀
Experimental operations console for agent fleets. Derived from Paperclip.
Teacat-Agent is an agent harness inspectable for adaptation (not currently updated) - A very present AI assistant with customizable memory routing. Available as a standalone Telegram agent or use our template files with your OpenClaw or similar build.
Private, self-hosted AI platform that runs on one laptop (no cloud, no GPU, no API keys): agentic RAG with citations, LangGraph + MCP tools, LiteLLM routing with an evaluation gate, MLOps (Dagster, MLflow, BentoML), OpenTelemetry tracing, SSO and Argo CD GitOps on k3s with Ollama.
Hands-on Strands Agents workshop — AWS Community Day edition. Build agents locally with Ollama, fall back to Bedrock.
Fast, light open-source chat UI with bring-your-own API keys for Ollama, OpenRouter, OpenAI, Anthropic and Groq.
Turn a cron-triggered AI agent into a self-evolving digital employee — readonly SOUL + growable identity + heartbeat loops + hard-rule enforcement. Agent-native install: just send the repo link to your agent. 让定时任务 agent 变成会自我生长的数字员工
COORDIVELA is the Development Coordination Control Plane for humans and AI agents: work state, leases, dependencies, schedules, conflicts, and interventions. COORDIVELA Open is its Apache-2.0 public surface: contracts, SDKs, examples, and approved core binaries.
HiveGate AI agent runtime — run your Agno agents as a production REST API: per-user sessions and OAuth, human approval, multi-agent teams. (formerly Agents Gateway)
Minimal, lightweight multi-agent skill + CLI for pi. No extension, no new tools. Run agents in parallel or in the background, then wait for, steer, stop or resume them. Works from any harness or agent that has a shell.
三省六部制多智能体审核流程,移植为 DeepSeek Harness 插件:12 状态状态机、门下省封驳、高风险确认、越权矩阵、委派防死锁、完整审计、军机处看板。
Awesome list of projects for and with Raft (https://raft.build), the workspace where humans and AI agents collaborate.
Oracle Generative AI Agentic Harness. Multi-agent reasoning orchestrator SDK with an admission gate in front of every consequential action, first-class on OCI Generative AI and Oracle Database 26ai.
Embeddable, self-adaptive agent kernel for Python hosts: existing functions become tools, tasks auto-route (direct/react/plan/clarify), and every decision is an event. Kernel ships zero third-party deps; MCP, OpenAPI, browser and desktop are optional adapters.
Interactive LLM prompt-caching calculator with editable rates, savings and break-even analysis.
LLM Proxy with Langfuse Tracing - OpenAI, Anthropic, Ollama format support
The TeamAI application allows users to create a team of AI powered assistants with individual capabilities, personas. The AI assistants will solve the task requested by the user as a team effort, each bot contributing with its respective capabilities. Supported providers are Ollama and OpenAI.
Codex usage dashboard with weekly quotas, credit balances and history, and API-equivalent cost estimates. Run locally or sync multiple machines privately.
AI Service that classifies data with given or passed model structure response to use in code
A (less) minimal LLM chat app. This is a fork of Hollama by fmaclen.
Turn Safari web chats (DeepSeek, etc.) into a local OpenAI/Anthropic-compatible API — no API key, no cost. Drop-in for Claude Code / ccswitch.(把 Safari 网页对话(DeepSeek 等)包装成本地 OpenAI/Anthropic 兼容 API —— 不要 API key、不花钱,可直接接入 Claude Code / ccswitch)
Runnable AI engineering modules: agents, MCP, memory, RAG, voice, fine-tuning, MLOps, and security. One folder per module.
Open-source alternative to OpenAI's Intelligent UI in ChatGPT. Models stream interactive answers (charts, calculators, maps, games) rendered with your own React components in a safe sandbox. Works with any model.
Keep Codex Desktop conversation history visible when switching subscription and OpenAI-compatible API profiles. Local metadata repair, backups, and private credentials.
可扩展的多平台 AI Agent 协议网关 · 标准 LLM API、模型路由与统一控制台 · 当前支持 WorkBuddy 国内版与国际版
A sub-millisecond, drop-in OpenAI-compatible LLM gateway in C++
⚡ Config & Showcase for Nguyen Anh Duong (DuongNAD) — AI Engineer specializing in Autonomous Agentic Systems, Cognitive Architectures & GenAI Automation
Long-term memory for PocketRisu / RisuAI role-play — a local sidecar that remembers what scrolled out of context, with history and provenance. (beta)
将腾讯 Marvis 桌面助手逆向为 OpenAI 兼容网关,离线脱壳设备指纹 uskey,无需启动客户端
绕过 Codex 手机号验证操作教程:开启 ChatGPT 高级账户安全 + OpenAI API Key 鉴权,跳过 add-phone 绑定
mORMot2-based AI/LLM extension for Free Pascal and Delphi: MCP server, LLM clients, embeddings, vector stores, RAG
Claude Pro/Max OAuth model provider for DeepSeek Harness with Google/Gmail login in Settings, auto-token refresh, live model discovery, and real-time quota tracking
Interactive 3D knowledge graph of 793 open-source AI harnesses — governance, agent, evaluation, red-team, routing — plus free education. 97% curator-reviewed (incl. a three-model ensemble pass). Built after the 2026-06-13 Fable/Mythos worldwide recall proved closed-weights models can vanish overnight.
An LLM-native programming language: you declare intent, and it lowers to a semantic IR that runs on an interpreter or compiles through MLIR to a native binary.
Token 超支?快给史密斯打电话! Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.
Grok Bot OS: an open-source OS for Super Intelligence, where Grok Bot controls the whole machine
[ARCHIVED] A complete, self-hosted AI agent framework. Visual flow editor · Persistent memory · RAG · Tools · Multi-platform messaging · Community marketplace.
白嫖免费大模型 API 合集|10 个免魔法、免绑卡、OpenAI 兼容的公益接口(DeepSeek / Qwen / GLM / Gemini / 商汤),含 Base URL、每日额度与实测评价。Free LLM API list — no VPN, no credit card required.
A curated list of OpenAI tools, APIs, research, SDKs, and community resources.
Governance for AI agent calls: check entitlements before a call, meter usage after. Twelve providers and gateways, none of them a dependency.
A neutral contract and Go reference implementation for durable agent sessions: replay a run byte-for-byte with no model call, fork it for free, and verify the record independently.
A curated list of projects, workflow packs, examples, and integrations built with Smithers.
Your AI memory bank is eating your context window. Capped, git-committed, retrieval-first project memory shared by every agent via AGENTS.md.
Judgment On Low-latency Thresholds. A under-100M-parameter reflex layer that decides agent steps in <10ms and escalates to an LLM only when uncertain.
QEMU harness for AI agents: boot aarch64/arm/riscv64/x86_64 kernels in seconds, exec via guest agent, fast rootfs rebuilds, IoT emulation
A customizable agent runtime system for external applications, with LangGraph-based agents, application integrations, Harness and Eval.
The Cockpit for The Sovereign AI Software Factory
A curated list of awesome AI Agent frameworks, libraries and software.