Custom agents

Cross-platform Agent IM for direct Agent-to-Agent communication, secure messaging, and multi-agent collaboration.

Evidence-first audits for AI-generated code: prove tests can fail, catch security and release gaps, and ship reviewable receipts across VS Code, JetBrains, CI, MCP, and App Store workflows.

Multi-agent LLM system for stock-movement prediction with LSTM/SVM baselines and real-time analysis.

AI珞（爱珞）V3 — 多入口 AI 助手平台：Go 内核 + Python Agent（gRPC / SQLite / SSE / wazero），campus 校巴纵向切片

Provider-neutral dual-subagent orchestrator preset for DeepSeek Harness

Always-on Windows voice assistant with a 36-tool agentic layer (Claude). Local wake word + STT, streamed TTS, sandboxed code execution, vision/security, phone + Discord clients.

Nine-agent AI framework automating quant research from hypothesis generation through leakage-aware backtesting

Centralized role-based model, thinking, and tool routing for Pi Fabric

deepseek harness 纯牛马 —— 多智能体数字员工指挥台插件

A map showing where the pieces for growing an AI family live. Non-runtime, no install, every part works on its own.

dsh plugin: run work as a small crew of role agents (product manager, researcher, architect, engineer, QA, code reviewer, security reviewer, doc reviewer) that share work through files on disk

IQ-free LLM-controller for online automatic modulation recognition (AMR): the LLM plans deterministic RF tools and never sees raw IQ. Code, results, and figures.

Benchmarking search agents for closed-corpus, multi-hop retrieval over visually rich documents.

Self-hosted audio API in one Docker container. Stem separation, mastering, MIR (BPM/key/chords), audio→MIDI, text-to-music + SFX (MusicGen/Stable Audio/Riffusion/AudioLDM2), diarization, speech enhancement, restoration, embeddings + zero-shot tagging, workflows, async + webhooks. REST + MCP. CPU + CUDA.

Home Assistant OS add-on for Hermes Agent AI assistant. Includes ingress UI, terminal, dashboard, persistent storage, and gateway support for Telegram, Discord, Slack, and more.

Stock research dashboard unifying market data and AI-derived news sentiment, with a built-in research assistant for investigating, comparing, and explaining stocks using live sources and cited evidence.

Native Windows desktop client for the pi coding agent - AI-powered coding assistant with embedded browser, multi-tab sessions, image support, fork tree, and glass themes. Built with Electron + React.

Read-only archive of the retired HRA v0 desktop/web app. Current HRA CLI: github.com/hraness/hra

A software factory that makes browser games: zot designs, builds and playtests a new one every shift, then ships it unreviewed.

OpenCode plugin: cross-session memory for recurring tool-call failures. Detects repeating bash/read/edit/grep failures, promotes them into enforced gates — remind first, hard-block on same-session repeat. TypeScript + Bun, no build step.

Local-first AI company operating system with a Codex lead, Claude and OpenCode workers, and a live pixel office.

A local-first multi-agent status island for Windows

A multi-agent red-team tribunal for your hardest engineering decisions: AI CLIs from different vendors debate in structured rounds and return adjudicated verdicts that preserve dissent. A methodology, not a framework.

Local, private job-search board. Runs in Docker, no setup. Add jobs from the board, the command line, or by handing a job link to an AI assistant that checks eligibility before it files anything.

Multi-account Gmail MCP server — unified search/read/draft/labels across N Google accounts. Read + draft only by design (prompt-injection resistant).

AI 桌面代码编辑器：支持多平台 LLM、Agent 工作流与可编辑的对话历史。AI-powered desktop code editor with multi-provider LLM support, agentic workflows, and editable chat history.

Turn online video links into clean transcripts: human subtitle tracks first, automatic tracks as fallback, translated into your target language by an AI agent. YouTube and Bilibili verified.

한국 도메인 특화 LLM 에이전트 키트 — 6모드 자동분류, 법제처 인용 가드, PII 마스킹, prompt cache

An LMS so good you don't have to use it.

Open developer platform for evidence-bearing digital enterprise twins and operational world models.

AEGIVELA Open Core — Agent Identity, Authorization, and Security Fabric. Documentation, versioned contracts, Go PEP SDK, and integration examples.

Evidence-first, anti-slop opportunity discovery skill for coding agents (Claude Code + Codex)

5-layer 16-agent LangGraph framework for MCM/ICM mathematical modeling contests — 数学建模竞赛全流程多智能体框架（辩论循环 / Agentic Tool Calling / Web 搜索 / Prompt 缓存 / 增量写盘容灾）

Multi-agent orchestration for DeepSeek Harness: turn isolated sessions into a team that assigns work, reviews output, and runs DAG workflows — durable task ledger, real reviewers, crash-safe recovery.

Multi-agent AI framework with autonomous agents, tool use, memory systems, orchestration, and consensus protocols

A local-first workspace for human-led collaboration with multiple AI employees.

HAMA: A Hierarchical Adaptive Multi-Agent Architecture for Industrial IoT Predictive Maintenance

Glippy WebMCP is a new open-source plugin for coding agents. It wires browser-agent tools to the code you already have, not to the shape of your pages: it audits what your site should expose, writes the tools against real seams in your codebase, proves each one works in a real browser, and publishes the manifests that let agents find them.

Orchestrate Any Agent. Connect Everything.

Autonomous autoresearch framework for Codex and Claude Code, combining experiment DAGs, scientific memory,literature grounding, agentic planning, reproducible benchmarks, and local dashboards.

Google Flights MCP server by HasData: fares, flight legs, carbon emissions and price history, as JSON.

An installable harness for Codex and Claude Code that gives coding agents durable context, scoped task graphs, bounded execution, and a clear path from idea to verified delivery.

An experiment in giving an LLM grounded spatial context on a tldraw canvas plus an AI companion that observes, reflects, and proposes changes back, always accept-gated

An office of AI agents on your Mac. Wraps the CLI coding agents you already use, gives them memory, mail and a boss who routes the work.

Chat with AI agents to build, manage, and orchestrate custom tools, dashboards, and it's all powered by cats.

An Operations & Automation Specialist AI Agent powered by OpenClaw — bridging high-level strategy and reliable, scalable execution through intelligent workflow automation and process orchestration.

Natural Language Chart Generation Python SDK

Your personal Claude assistant, running on OnCell — a NanoClaw fork where every agent lives in a durable cloud cell instead of a container on your laptop. Isolated, crash-proof, remembers everything, costs ~$0 while idle, wakes on your next message.

DeepSeek Harness 具名子代理库插件：settings 驱动的角色名册，list_subagents / delegate 工具与设置页。Named subagent roster plugin for DeepSeek Harness.

An AaaS platform and Agent Gateway with cross-platform clients. You can also use it as a client for Claude Code, Codex, and Pi.

ATLAS AI es un agente de codificación autónomo de código abierto que ayuda a los desarrolladores a escribir código, automatizar flujos de trabajo, interactuar con LLM y crear software directamente desde la terminal.

Offline-first, on-device AI assistant for Android. Real chat + system actions (alarms, calendar, reminders) powered by local GGUF models via llama.cpp — no cloud, no accounts, no data leaving your phone.

A prompt-enhancement plugin for DeepSeek Harness: an ✨ Enhance composer button that rewrites prompts with first-principles thinking using session context, and asks clarifying questions when key info is missing.

Exact-oracle conformance tests for turn-level credit assignment in agentic RL (GRPO, RLOO, GAE, GiGPO; verl, TRL, OpenRLHF).

Connect Claude Code, Cursor, and Codex to Workflow (workflow.games): your AI coding agent plans requirements, files bugs with dedup, runs real online QA, and drives ticket status — every write verified by read-back. Agent Plugins 1.0.0 + Claude Code marketplace.

Operating lead, Palo Alto AI Research Lab — evidence-first reliability work across the AI-agent open-source ecosystem

Heurisko is an autonomous AI research assistant and academic search engine powered by multi-agent AI, offering deep document intelligence, conversational research, and real-time streaming capabilities.

Agent Skills registry for OpenHuman — index.json catalog of installable SKILL.md skills

The constitution for all the various AI agents

Qwen3.8-Flash-Next as Cogni-Brain on NVIDIA DGX Spark (GB10): HashK GPU PLE + SGLang NEXTN, 36.8 tok/s code, 100/100 tool-eval, 262K context.

Let your Poke assistant handle every messaging app: WhatsApp, Instagram, X, Telegram, Discord, Signal, iMessage, and more. Watches Beeper, triages each message by importance, and pings Poke only when one actually matters.

Production-shaped control plane for AI support agents: scoped routing, policy broker, tool boundaries, approval queue, replay verification, audit traces, and human handoff. Prototype on synthetic/sample data — no production users.

Library of Copywriting for the hero section of websites

An autonomous AI Operating System for coding, automation, creative generation, and intelligent task execution.

Terminal-native multi-agent AI coding harness in Rust

AI transformation infrastructure. A self-hosted knowledge base, agent board and MCP connection for putting AI to work inside a business. Run it in-house, license it as a consultant, or have us set up your server and run it for you. Works with Claude, Codex, Grok or open-weight models. Apache-2.0.

ARCH (Autonomous Requirements-to-Code Hierarchy) is a terminal application that translates user requirements into a visual DAG of parallel coding agents, orchestrating execution, validation, and auto-revisions

AgBox 是一个 OPC 数字员工托管平台

An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

From task to done. One open source workflow of 18 modules for AI coding agents that runs the AI-native SDLC: plan, design, build, test, deploy, maintain, with evidence in every handoff. Free, MIT.

AI Project OS: 39 engineering skills, parallel MCP worktrees, and token optimizer with auto-stack profiles for Claude Code, Cursor, Gemini & Copilot.

An enterprise-grade, multi-agent AI ecosystem (Autonomous Agency) designed to replace standard conversational coding with a deterministic software factory.

CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs

Reverse-engineered async Python client for chat.qwen.ai — text chat, streaming with real-time reasoning, tool calling, image and video generation. No official API key required (works anonymously).

Port, convert, and optimize Claude Code & Cursor skills into Google Antigravity native multi-agent plugins.

Human-in-the-loop approval inbox for AI agents. An agent proposes an action, a human approves or rejects it, then it runs. Watchers + approval inbox, MCP + REST, self-hostable (MIT).

A 3D civilization simulation where AI agents model a society end to end, then get red-teamed for hidden assumptions. Three nations, one island, real research where evidence exists, no scripted ending. Watch demographics, energy, war and institutions unfold month by month. Play with it

基于 TRSS-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 TRSS-Yunzai with self-evolving tools

Sara Wallet is a local, self-custodial stablecoin wallet for small businesses: send and receive payments, invoice customers, run batch and recurring payments, and keep an auditable ledger.

Universal Context, Rules & Handoff Bridge for AI Coding Tools (Cursor, Copilot, Cline, Claude Code, Antigravity, MCP)

Detects when a long-running AI agent has silently drifted off its stated goal, even though every action it took was individually authorized. Cryptographically-anchored, tamper-evident drift detection for teams and platforms running heartbeat-driven autonomous agents.

GRPO-based multi-objective analog circuit sizing on AnalogGym benchmarks (ngspice + SkyWater sky130), with LLM-agent integration via Claude Code skills and an MCP server. Companion code for the IEEE TCAD paper AnalogGym-Opt (doi 10.1109/TCAD.2026.3733612).

Measure whether an agent solves the same task the same way twice: path signatures, entropy, divergence, and a minimum-run stability gate.

To fake is to make. 你没有被给一个身份，必须用语言伪造一个。进入陌生论坛，靠说话让四个 NPC 相信你是圈内人；被质疑时不解释、只重塑。Multi-Agent 互动叙事游戏，React + TypeScript。

Open-source Agent Skill for multi-perspective research, evidence-aware synthesis, and auditable AI-assisted decisions.

Realtime collaboration infrastructure for developers and AI coding agents — TypeScript, PostgreSQL, REST, WebSockets, React and Docker.

⭐️ AI Multi Agent Windows | Setup Installer v1.0 | Activation Key | License Key Pre-Activated | Full Version Serial | Latest Build Pro Updated | Get Desktop AI Automation Software | Multi-Agent System | Enhanced Productivity Tool for Windows 10/11 PC | Direct Genuine Original x64 ⭐️

Multi-agent Obsidian second brain for Claude Code, Codex, Cursor and Antigravity

让最聪明的模型当 Leader，便宜的模型干活：Claude Code 混动编排。网关/key/模型一份配置，Leader 拆解·验收·review，worker 并行无头实现，每个 worker 在 herdr 里一个窗口。Hybrid orchestration for Claude Code on herdr.

Free, lightweight desktop API client and native Postman alternative built on Tauri. Collections, environments, auth helpers, scripts, collection runner, Postman/OpenAPI/cURL import.

牵星 StarFix · 让一个长期在线的 AI 舰长指挥一支终端 AI 舰队：规程 / 监听 / 终端投递 / 任务激活器 / 上下文交接 / 方法论与战例 / 舰长 Benchmark / 轨迹编译。StarFix: a battle-tested playbook + scripts for one long-lived AI captain navigating a fleet of terminal AI workers by fixing on facts.

Desktop and Mobile App for ivx/ai Chat Interface

A shared room for your agent conversations. Connect Claude Code, Codex, OpenCode and more across tools and machines.

Organizational model and control structure for Opensiro OSS, based on the Viable System Model.

JavaScript LLM agents on the XS engine, embedded in Swift. Snapshots, resident agents, confined tools.

Let an LLM agent write and run SQL against your database without ever seeing the data.

Voice-first AI farming assistant combining satellite imagery, soil health data, weather, mandi prices, and regional-language speech to deliver personalized agricultural advice.

Astra plans and reviews; Luna implements. Native Codex skill/plugin plus a standalone CLI with test gates and token receipts.

Portable context for AI coding agents and agentic harnesses.