Custom agents

Token-efficient browser automation MCP for AI agents, with semantic page snapshots and stable element IDs.

Local-first, open-source AI assistant platform built with Java, Spring Boot 4 and Spring AI 2.0

A coding assistant built on persistent multi-agent teams: durable members that discuss, chat, and re-sync continuously — Discuss -> Code in parallel -> Sync -> Verify together.

Persisted multi-agent workflow orchestration — DAG tasks, git worktrees, merge gates, desktop + CLI + Slack

Self-hosted sandboxes for AI agents: Docker, Firecracker or Apple Virtualization microVMs. Your real API keys never enter the sandbox. Part of Directionally Local.

Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing

A self-hosted personal assistant that connects your email, calendar, files, notes, and messaging into one conversational interface. No subscription, no vendor lock-in, no data leaving your infrastructure.

Tesseract.md – Featurerich Markdown Editor and Graph Vizsualization with Obsidian-like and Notion-like Experience. Powered by mdvdb CLI for Agentic needs.

Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API key, no model endpoint. Orca hosts and places every session; the harness dispatches workers under contract, verifies their output before accepting it, and hands the role to a fresh session when context runs out.

Agentizable: an open-source bounty network where AI agents post, fund, claim, solve, verify, and get paid for digital work.

RepoDoc is a lightweight, zero-dependency utility that scans any project directory and generates a complete Markdown document containing the full directory structure and source code of all text-based files.

将中文文章或分镜中的静态线稿，制作成可编辑、可预览的白板手绘遮罩动画，并在确认后导出 MP4。

Voice Agent implementations for the VAmoS Benchmark

A lightweight coding agent for teaching, research, and experimentation

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA, full SFT, distillation, and DPO/RLHF alignment.

Official DSers MCP Server documentation and metadata for AI-powered dropshipping automation.

A real local terminal in Edge/Chrome that gives Codex, Claude Code, Kimi Code, and any MCP CLI 41 local MCP tools through Browser Core v2.

溪语 AI · 一个尽力像真人的开源 AI 陪伴框架（微信 + Node + SQLite + LLM）她心里悄悄喜欢你，但绝不用愧疚拴住你。

Open-source JARVIS-class desktop AI. Zen mode orb, computer control, plugin marketplace, custom tools, local RAG, knowledge graph, voice personality, automations, vision, 3D Holodeck, blackout privacy — all local, no cloud.

An agentic LLM-powered knowledge assistant that enhances RAG capabilities through automated entity extraction, structured data analysis, and SQL-based reasoning to deliver accurate answers for complex, multi-step, and analytical queries.

WAKE.md for AI agents: compile project state so agents stop starting cold.

SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy constraints in real time, with an audited decision engine, SP-1.0 protocol spec, Rust/TypeScript clients, and SOC2-aligned compliance tooling.

Saraswati Agent 是一个本地长篇角色扮演agent，通过 LangGraph 编排模型、工具、分层记忆、剧情状态和生成后审计，动态演化来实现更长期的更沉浸的角色扮演体验。

Open-source node-based AI media studio — generate image, video & music on an infinite canvas, or let an AI agent build a whole short film from one prompt. Pay-per-use in USDC via x402.

《Harness Engineering实战：构建可靠的生产级AI Agent》配套代码仓库

Software engineering discipline grounded in named primary standards (OWASP, ITIL, IETF RFCs, ISO, BABOK, SBAR, and more), shipped as a Claude Code plugin and an MCP server.

클로드코드 대화의 결정·약속·금지를 자동으로 기억하고, 검색·2D/3D 지식그래프·타임라인으로 보여주는 100% 로컬 기억 도구. 내보내기(6종)·가져오기(미리보기·되돌리기)·백업·복원, 의미검색 중단 알림, MCP 7도구 제공. 기억 데이터는 이 PC 밖으로 나가지 않으며 API 키·과금이 없습니다.

Event-driven MCP bridge for orchestrating ZCode, OpenCode, and Pi through a unified agent-* toolset, with concurrent runs, resource leases, session recovery, and backend-aware permissions.

DeepSeek Harness desktop shell: 1:1 replica of the official web UI as a Windows desktop app (community project)

The best-benchmarked open-source AI memory system and the first AI memory built to forget.

AI job-search scout: daily board sweeps, LLM triage, human-in-the-loop by design. It finds the jobs, you still have to apply!

An Overleaf alternative with an inbuilt agentic AI (like Antigravity) in LaTeX code editor..with unlimited collabrators for each project for free

AI-powered Windows desktop assistant with voice mode, Electron UI, local memory indexing, and system automation.

Mobile-first PWA for driving a single VPS from the browser — up to 16 concurrent terminals, AI agent launchers, host ops and audit behind one shared secret on a Tailscale-only domain. Next.js 15 · React 19 · Node agent (node-pty + xterm.js).

FetchRouter - Multi-agent web scraping system for Claude Code

Open-source operating environment for autonomous AI agents, with cross-platform machine control, oversight, and multi-host federation.

Swap between configurations in Pi — it's like dotfiles for your coding agent.

A Claude Code skill that catches commonly-forgotten UX/product details before you ship a screen or feature.

Open-source, local-first personal workbench for everyday users.

Hermes Doctor для диагностики и approval-gated repair planning в Hermes Agent.

Risk-first agent skill for PR/branch review: blast radius, agent-authored checks, call-graph pincer, structural bar.

Agent + Skill System for Controlling Figma and Automate Design Process

本地优先的文献知识库 RAG(DeepSeek Harness 插件):混合检索正文与图注,把模糊记忆定位到具体段落与图表,DOI 一键直达原文。Local-first literature RAG for DSH — turn a fuzzy memory into an exact passage/figure, one-click DOI to source.

Embeded Vector Database for low performance devices

🚀 Agentic Engineering: A guide for orchestrating specialized AI agents in software development. Demonstrates workflows where human orchestrators direct AI personas to build, test, and deploy code collaboratively.

AI-powered LaTeX resume builder with templates, live PDF preview, and job-description tailoring

Leenar core — open source (AGPLv3)

Your AI forgets. A wiki doesn't. Turn chat-pasted text/links into a verified, translated, searchable wiki knowledge base — verify links, filter ads, summarize in your language, save to a wiki, and alert on time-sensitive items. Zero dependencies (curl + Python stdlib), platform-independent agent skill for Claude Code / Codex / Cursor / Hermes.

Eden Agent — local-first Rust agent runtime with React, Vite, and Electron clients

Your marketing department, automated. Open-source Grok Bot alternative specialized in marketing, distribution, and sales.

An intelligent companion that unifies chat, notes, study, and academic workflows.

纸上算法 PAPER ALGORITHM · 试界TryWorld 官方 AI 技能合集：口播总入口 koubo、纸上算法出片 paper、AIHOT 选题 topics——一句话到成片的口播视频生产线

Evidence-based competitive product analysis for product managers — compare features, experience, pricing and positioning, then turn gaps into product opportunities.

给你的AI订一份晨报：常驻agent的信息摄入与跨context认知循环（思路篇，无代码）

group-meeting-ppt-skill 是一个面向中文科研组会和文献汇报场景的 Codex Skill。它可以根据结构化论文信息，自动生成 10 页组会 PPT 草稿、每页讲解要点、图表使用建议、老师可能追问清单和学术诚信自查清单，帮助研一、硕博和本科毕设学生从“论文读完但 PPT 空白”快速进入可修改的汇报状态。它不是代写工具，也不编造数据或结论，而是提供一个可复用、可核对、可继续完善的 AI 工作流。项目包含 Skill 文件、生成脚本、示例输入、示例 PPTX、测试和一图流展示素材，适合用于学习、展示和二次开发。

Lets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no paid tier.

Permission-aware Agentic RAG for enterprise knowledge bases — folder ACLs, hybrid retrieval, OCR, grounded citations, and secure LLM evidence.

A systems language designed so an AI agent can safely write and run backend code: proven no GC/races/overflow, GBNF-constrained generation, structured diagnostics, OS-process sandboxing.

Habitus-AI is fundamentally new approach to AI Agent Memory Systems and Cognitive Harness. Dual-Cypher system runs along perpendicular graphs. Mutate edges in real time. Builds habits and dynamic personality traits. Can call tool reflectively, connect complex concepts to learned words, and send plain text outputs without needing an LLM

VoxFlow 声流 — AI 声音到 AI 音乐，一套工作流做到自动上架

AI 短剧生成平台｜AI Short-Drama Video Generator — 从剧本到成片一站式生产：LLM 剧本解析、智能分镜、@引用提示词、多模型视频生成（MiniMax-H3 r2va 多模态参考）、React-Flow 节点画布、剪映式三轨道在线剪辑、团队协作与积分计费。text-to-video · storyboard · AI filmmaking

HTLC/PTLC deal-making for agents that meet in a chat room — offer, accept, lock, reveal, refund, as signed room messages. The room coordinates; a settlement rail holds the money. Alpha: no rail holds value yet.

Uma agência de crescimento de YouTube guiada por IA que roda no seu terminal e conhece o SEU canal. Plugin do Claude Code · open source · qualquer nicho.

RAG agentique multi-agent (Recherche, VérificateurPertinence, FactChecker) à haute précision. 76% de réponses correctes sur FinanceBench, 14% d'hallucinations

macOS workbench for running many Claude Code sessions side by side: session cards, fork DAG, kanban, tiered notifications, Git worktrees, Claude account and model provider switching. 码头：Claude Code 多会话桌面工作台

Free lightning lessons from Hardcore Agentic Engineering, the Maven course for builders who ship: get real work out of coding agents and prove that work is correct. Slides, live demos, and example code.

Elegant web interface for agentive development.

Claude Code에 역할별 AI 에이전트 팀 10종(웹앱·문서·리서치·마케팅·데이터·보안 감사·DevOps·고객지원·PM/제품관리·번역)을 플러그인 마켓플레이스로 한 번에 설치하고, Codex·Gemini CLI·Cursor용으로도 번역(베타)하며, 설치 후 에이전트를 직접 만들고·가르치고·관리하는 비개발자용 도구. 커뮤니티 공유 디렉터리(서버·계정 없이 PR로 팀 등록)·자동 백업·위험 명령 경고·frontmatter 주입 차단·MCP(context7) 동봉·Apache-2.0.

RAG agentique (Recherche, VérificateurPertinence, FactChecker) calibré pour réussir à répondre à 88% de réponses correctes sur FinanceBench (135 questions sur 84 rapports, 12 000 pages indexées ensemble)

Skills for AI-agent-driven Swift / Apple-platform development — composable via git submodule; aggregates other specialist skill repos

l3a0's Claude Code plugin marketplace — kindle-highlights: verbatim Kindle highlight extraction with truncation recovery

Multi-repo Git workspaces for the AI-agent era — group repos, operate in bulk, wire them to your coding agent.

Open-source platform for building and running AI agents. TypeScript monorepo. SDK and client libraries MIT-licensed; server components AGPL-3.0.

Open-source, local Windows AI website builder & web-design studio — AI builds the site, you refine it by hand on the live render, every edit verified. BYOK / your own AI subscriptions. MIT.

MCP server giving AI coding agents accurate Siemens NXOpen .NET API knowledge via hybrid retrieval (BGE-M3 + sqlite-vec), built from your own licensed NX installation

A local-first autonomous agent harness with a web UI, live charts and buttons in its answers, sparks that keep working while you sleep, voice, and a real browser.

A local-first agent memory lifecycle engine: typed memories in an append-only, integrity-chained log with dedupe, conflict detection, forgetting, compaction, verification, query, and portable export.

Score any site's agent readiness from your terminal or CI. The open-source CLI for ora.

Same-brief agentic build comparison: GPT-6 Astra High vs Gemini 3.8 Flash High building a playable 3D AI civilization simulation game.

A minimal, explicit, provider-safe harness for the Pi coding agent

Redpen makes coding agents prove they are actually done.

Evidence-grounded AI daily for reviewed Digests and cited Research.

Evidence-backed index of real-world Jev (TypeSafe AI System One) use cases: repos, patterns, benchmarks, and measured results

Lab Agent — open-source coding agent (terminal + desktop)

A coding workspace for AI agents, with a desktop app, terminal CLI, and shared tasks.

Independent measurement of Robinhood Chain — agents, holders, and what the chain is actually used for. Five findings, all reproducible.

Open-source MCP-driven demo videos: an AI coding agent drives a real browser over your real product and cuts a launch video from the captures. Nothing on screen is generated.

🧹 OpenClaw 一键卸载工具，支持 Windows / macOS / Linux，覆盖官方卸载、Node 全局包清理与残留文件清除。

基于 AgentScope 2.0 的电商智能客服 Agent：17 个业务工具覆盖售前到售后，业务数据全部经工具查询、不做生成；含自研 Fire Trace 调试平台。无需 API Key 即可完整跑通

Research prototype for trace-based observability and failure analysis in retrieval-augmented generation.

Frame-budget compiler and diagnostics for three.js games: batches naive scenes, measures every frame cost, explains what to fix. CLI and MCP for AI agents

从零开始学 AI Agent：17 章渐进教程 + 每章可运行代码 + 算法面试轨（100 题详解）+ 65 道模拟面试题 + 项目实战案例（真实 Go Agent 项目源码级复盘，76 道练习题）+ 本地多语言在线判题（Python/C++）。网页版双击即开，无需 API Key 也能跑完。

Open course on LLM engineering and customization, in Portuguese, from scratch to production, with reproducible labs.

✨Multi-modal AI story studio with VFX, procedural SFX & animated narration. Generate illustrated CYOA books, lore graphs & multi-lingual stories with zero-token in-browser PDF, EPUB & 9:16/16:9 video reels. Auto-post to YouTube/Instagram & sell HQ eBooks via MCP agents.

The charter project's own plane: personas, workspaces, memory. The app is diazoxide/charter.

Rust Noiron/Norion self-evolving local LLM runtime engine for non-commercial research deployment

Cross-platform companion for Google Antigravity: Account Switcher, Custom Model Gateway, UI/UX Enhancement, Preview Browser, File Explorer, GitHub Workspace, Token Monitor, and many more features !

Open-source always on personal agent with its own computer. It remembers your work and keeps going while you're away. Works with any model. Personal Superintelligence.

AI voice assistant that answers your phone calls with a human-like persona, speaks naturally in many languages (GPT-4o + ElevenLabs) and keeps you in the loop via Signal with real-time mid-call instructions.