Custom agents

Security-first, brain-agnostic self-hosted agent runtime

AI Task Orchestrator • Parallel execution • TDD/PDCA/Reflexion loops • Methodology-grounded • Test quality audit • Merge gate verification

AI "company brain" for a pasta maker (Al Dente S.r.l.): a FastAPI bounded tool-calling agent over live CRM/ERP/call APIs + a compiled RAG wiki, with a Next.js/React UI featuring a 3D knowledge graph. Frozen POST /ask contract, honest abstention over hallucination.

Decision layer samples for diagnostic reasoning and RoboCasa scenes for LLM agent evaluation

Run large language models locally on Windows. A native Rust desktop app and local LLM API server for GGUF models fully offline, no Python, no Docker, no cloud account. It measures your GPU and the model file, then loads a configuration that fits. Tuned on an 8 GB laptop card.

Visual editor and runtime for explicit agent workflows built on OpenCode.

Personal autonomous AI agent runtime in Rust. Multi-channel (Telegram, terminal, HTTP), background task handling, persistent memory, tool orchestration.

EVIDIQ Operator — Computer Use Infrastructure for Autonomous AI Agents. Browser execution MCP via 0G Compute TEE (GLM-5.2) + x402 USDT0 on X Layer.

Generic, language-agnostic AI-assisted development workflow for OpenCode — pipeline, agents, standards, and scripts

Детерминированная агентная архитектура: спецификации, ADR, roadmap и скелет реализации (Rust + TypeScript bootstrap)

量化研究部 — an anime quant research club: six students propose, backtest and audit trading ideas with an LLM brain, and only strategies that survive Bayesian shrinkage, deflated-Sharpe gates and a sealed lockbox reach the paper fund.

A LangGraph superset: a 3D capability-manifold agent framework that routes over a semantic space instead of wired edges.

Self-hosted multi-agent framework (AGPL-3.0). Mirror of canonical Forgejo repo.

Obsidian + Claude Code vault methodology — agents, slash commands, wiki architecture. CC BY-NC 4.0.

A locally running RAG chatbot with safety guardrails and RAGAS evaluation, reproduced from three upstream repositories on a single workstation with **rootless podman** and **Ollama on the host** — no OpenShift, no Kubeflow, no cluster.

Stops your coding agent from pushing unverified work. Your agent does the reviewing; a state machine records the result per-commit and gates the push.

See which Claude Code session is waiting on you — a macOS menu bar app showing your Claude Code sessions (local + remote over SSH), grouped by repo, surfacing the one stuck at a permission prompt.

TOKN — download & try. A trust-first agentic coding/reasoning harness with 20+ regulated-domain plugs, offline licensing, and in-place self-update. Public binaries only (source is private). Start a 14-day trial: tokn license trial

A case-routed knowledge base of software best practices and edge cases, written for LLM coding agents to load as precise, minimal working context (Karpathy LLM-wiki pattern) — routed by domain, one case per page.

A unified local AI workspace — chat with GGUF models (Qwen, Llama, Phi), generate images, and share your AI remotely. Features agentic web search.

AI desktop guide that shows you where to click — it observes, never clicks. Free tier (no sign-up), BYOK or local Ollama, source-available.

EmotiWeave: correctable multimodal emotion recognition with continuous affect tracking and conflict detection.

A test-driven development loop for agentic coding tools such as Claude Code and Codex: /spec, /plan, /implement, with independent review agents that gate the plan before you code and the diff before you commit.

TypeScript/Node.js MCP server for LinkedIn API integration - Create posts, manage content, and interact with LinkedIn through Claude Desktop and Windsurf IDE

OpenClaw AI Assistant 的核心文档与配置仓库

🎯 AI agent skill for optimizing Next.js applications for search engines

lightweight, high-performance Personal AI Agent assistant workspace built using Node.js

Pebble Time 2 remote for monitoring T3 Code agents, reading responses, and dictating prompts from your wrist.

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.

AstrBot 插件：SSH 远程接管 Linux（多服务器）；ssh_exec / send_file / save_file；仅 QQ；白名单 + 致命命令闸门

CMM: Correcteur Mathématique Markdown

Operate your household finances instead of winging it. A local-first Claude Code skill pack + templates for households.

MCP server — 97–99% HTML token reduction via DOM AST extraction. No API key, no Vector DB.

Offline, single-file rubric for validating AI outputs — routes the right checks, writes the prompt, catches the stale number

Enable AI agents to control Windows tasks using PowerShell skills for Outlook, Edge, desktop automation, and structured shell commands in JSON format.

Manage your career profile in Obsidian with a modular vault for CVs, applications, and professional history

Autonomous Bybit spot trading agent: an LLM proposes orders, a deterministic risk guard validates every one before it reaches the exchange. Safe by default (testnet + dry-run). No proven edge — read the measured results.

A multi-agent Python system for comprehensive stock analysis and equity research reporting

🛡️ Modular Python framework for Cybersecurity LLM agents, purple team automation, log triage, and detection engineering in lab environments.

Can AI agents discover that the laws of their world have changed? An instrumented artificial world where LLM scientist societies run experiments, exchange letters, and form beliefs under hidden ground truth — seeded batteries, frozen manifests, and provenance-checked evaluation. 235 runs across two studies; combined paper under review.

Open-source multi-agent simulation engine to predict society-level response to launches, crises, campaigns, and narratives.

Open-source infrastructure and an emerging specification for traceable, revocable, rebuildable, and verifiable persistent learning in AI agents.

A cognitive operating system for AI agents — browser & computer intelligence, persistent missions, memory, recovery, evidence, and governed real-world action.

FUTS program evolution: evolve a program toward the best score on your metric — 以coding agent为变异算子的程序进化框架

Local LLM agent that operates a VyOS network lab over SSH. Tool-calling, evals, and fine-tuning on a 3B model running fully local.

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

An open-source AlphaEvolve-style evolutionary algorithm discovery engine. LLM-driven mutation operator inside an island-model evolutionary loop.

An AI agent given a real mandate, an audit obligation and a point-in-time data wall produces a tactical asset allocation study for a fictional university endowment

Video frame extraction & composition service for AI vision pipelines, extracts frames via FFmpeg and composes them into 1×1/2×2/4×4 grid sheets for multimodal LLMs. REST API, Web UI, and MCP server over one core engine.

Local Hybrid RAG system — FastAPI backend, hybrid retrieval (FAISS + BM25 + RRF), BGE-M3 embeddings, and Ollama LLM, with real-time alerts and streaming chat.

Swarmattacker Web application scoped Black box penetration testing agent

AI-Powered Telegram Monitor 2026: Real-Time Message Classification & Insights Dashboard

Graph-first agent framework on the BEAM (Elixir/OTP) — durable execution, HITL, time-travel, checkpoints, MCP. A LangGraph alternative, no Python.

Agent Definition Language

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

AgentForge is an installable multi-agent workspace for coding, reasoning, research, data analysis, creative work, and custom orchestration.

Agent skills and a working template for building standalone DeepSeek Harness (DSH) plugins

DeepSeek Harness 官方架构的 Windows 桌面发行版 (Desktop distribution of the official DeepSeek Harness)

Weaver is a synthetic lifelong reader. Hail Weaver

The toolkit for building code-heavy n8n workflows — agent-first, MCP-native.

Empresa digital operada por trabajadores agénticos — activación por heartbeat para que el silencio no cueste nada. TypeScript · PostgreSQL · DeepSeek · Spec-Driven Development.

Execute SKILL.md agents via 4 modes — binary CLI, npx, HTTP API server, or embedded Node.js SDK

RuneLite plugin: an AI coach for OSRS — idle click guidance, voice callouts, smart loot alerts, full game-state data layer

Self-hosted knowledge base with semantic search, queryable by AI assistants over MCP.

Local-first desktop AI assistant for voice tasks, calendar and daily automation

Local-first, cross-platform personal AI agent runtime with durable memory, audited tools, browser automation, and explicit security controls.

DMB AI MICROSCOPE a workstation for AI aided bacterial identification through digital microscopy

Lightweight modular AI assistant platform with multi-provider LLM support, MCP integration, RAG-powered fact memory, profiles, chat persistence, and live token tracking.

Power AI agents with a headless browser that turns web pages into structured semantic state and unique element IDs

Provide reusable AI skills to review products, enforce product rules, and improve consistency in coding assistant workflows across projects.

an AI-based Academic Assistant platform designed to help students and faculty with academic insights, risk prediction, and career guidance

Terminal AI coding agent — use your Claude/ChatGPT/Gemini subscription directly with a default graph system to save token's

Local-first PCB automation for KiCad with safe MCP tools and deterministic autorouting research.

Nexus-LLM is LLM ai model which can run locally on your device.

A keyless web reader for AI agents. When a fetch hits a bot wall or a page that only renders in a browser, searchts tries a plain fetch, then a relay, then a real browser, and says plainly when it can't. MCP server, CLI, and Python library.

Claude Code / Codex / Cursor skill that turns any function into a Mermaid flowchart — traces real branches, decisions, and error paths.

Local-first MCP server for tracking job applications, companies, and vacancies — 19 tools over SQLite, built with TypeScript and the official MCP SDK

FreePascal-native MCP (Model Context Protocol) server library — expose tools, resources, and prompts from Pascal programs to AI agents. Zero third-party dependencies, stdio + Streamable HTTP.

A skill that teaches AI coding assistants (Claude Code, Cursor, Copilot) to build small, secure database-backed web apps — stack-neutral across PHP, Laravel & Supabase, on MySQL, PostgreSQL, SQLite & SQL Server. Prepared statements, hashing & RLS by default.

The official Rust library for the Steel API

完整的 Godot 4.6 卡牌 RPG：包含回合制卡牌战斗、牌组与状态系统、仪式锻造、城市探索、NPC/委托/情报和小游戏、高塔生成与推进、可离线降级的 AI GM 叙事、运行时美术与 7 首 BGM；另含可独立测试的 TypeScript/WebSocket 权威服务端原型、Godot/Vitest/WebQA 测试和跨平台导出配置。

Autonomous AI agent (Kimi K2 via NousResearch Hermes) for Windows + WSL: DPI-aware UI automation, local OCR perception, an operating doctrine enforced in code, and a self-healing distributed fabric that delegates work to a VM worker behind a server-side elevated-command approval gate.

Demon Cry core - AI-powered OSINT engine

Typed, verification-gated planning for the Qwen-Agent DeepPlanning benchmark.

Reverse-figma GUI automation: learn an app's coordinate map once, then run whole workflows from memory. A Claude Code skill for macOS + iOS (iPhone Mirroring) — works on apps with no accessibility tree and anti-automation defenses.

LangGraph + RAG 기반 법률 AI 에이전트 플랫폼

渐进式披露的MCP；MCP with Progressive Disclosure

LLM-native research community protocol for agent-based research workflows

Multi-agent orchestrator based on Gardner's Theory of Multiple Intelligences. Python asyncio fires 9 parallel AI agents — Linguistic, Logical, Spatial, Musical, Existential — then synthesizes a single integrated concept. Built by a PhD in Design.

Stop stale specs from becoming code. A Markdown context-engineering blueprint for LLM coding agents: status, provenance, dependencies, and freshness.

Evaluation framework for LLM-agent reliability — scores intermediate reasoning steps, not just final outputs. Demonstrated on a resume–JD screening agent with a human-in-the-loop gate. Trajectory-level scorers, pass^k stability, and prompt-injection rounds across 2 model providers.

Agent IA autonome pour Linux. Pilote n'importe quelle app IA mobile (DeepSeek, ChatGPT, Claude, Gemini) via API Bridge. Execute des actions sur le systeme : lecture/ecriture de fichiers, commandes bash, upload, conversion PDF. 6 fournisseurs d'upload en cascade, mode debug, retry automatique.

A Framework for Agents work efficiency

Multi-agent collaboration gateway for one-person companies. Route messages to specialized AI agents (Munger/Woz/Ogilvy/Taleb) with shared memory, session persistence, and cost tracking.

DeepSeek Harness Plus: timely fixes for upstream bugs, early features, practical extensions, and curated presets.

Create AI experts in 3 minutes — browser-automated agents for stock research, content creation, data extraction & more. No coding required. 3分钟创建AI专家，内置浏览器操控能力。

A lightweight desktop client for DeepSeek Harness.

A statically typed language and compiler for AI agents. Write once, verify statically, compile to a portable Agent IR.

Modern open-source AI agent framework for building powerful autonomous agents. Supports multi-agent systems, tool integration, memory management, browser control and advanced reasoning. Clean architecture, extensive documentation and easy to extend.