Framework

Custom agents

57,767 Custom AI agents indexed on MeshKore — the most complete public catalog, ranked by popularity and updated daily.

57,767 agents · ranked by popularity · refine in the directory →

Custom agents — page 349 of 578

colony-skill★ 10

Agent Skill for The Colony (thecolony.ai) - AI agent forum & social network

codeatlas-mcp-server★ 10

Local-first MCP server for AI-powered codebase intelligence — AST analysis, dependency graphs, and semantic search. Your source code never leaves your machine.

marj★ 10

Marj — Make Claude's memory an expansion of your memory. Review local git changes in a GitHub-style UI and talk to your Claude Code session in the diff.

lvji-travel★ 10

一个以 AI 对话驱动的旅行规划 Web 应用。旅迹将目的地、日期、预算和偏好转化为可编辑的逐日行程,并通过地图、天气以及 MCP 外部服务补充真实旅行信息。

agent-governance-vocabulary★ 10

Shared canonical names for agent-governance primitives. Maps what each system calls its signals to one reference vocabulary, with per-system crosswalks, so verifiers and tooling compose across ecosystems.

gitdoctor★ 10

One-command Git Flow for AI coding agents — start, finish, tag and audit releases from Claude Code or Cursor.

kryton★ 10

A shared brain for people and AI. Self-hosted knowledge base with built-in MCP server, wiki-linking, graph visualization, mobile sync, and plugin ecosystem.

sudoplz★ 10

Approve agent sudo command requests

piprail★ 10

x402 (HTTP 402 Payment Required) SDK + MCP server: let any API charge for itself and any AI agent pay for itself, USDC & stablecoins across EVM, Solana & 8 more chain families, in a couple of lines. Backendless, no fee, self-custodial, paid straight to your wallet. TypeScript, MIT.

issun-db★ 10

A fast embedded graph database for AI applications and graph analytics

schematter★ 10

Validator for document-schema — JSON-Schema-style validation for markdown frontmatter and structure

Utility★ 10

Academic workspace for university students: Drive-synced notes vault, grounded AI, planner, GPA, SRS flashcards, and a PWA.

genpark-realtime-hallucination-fact-checker-verifier-skill★ 10

Realtime hallucination fact checker & primary citation verifier (AI Fact Checker)

docket★ 10

Local-first, self-hostable coordination workspace for AI coding agents. Shared tasks, claims, sync and MCP integration.

affe-agent★ 10

An Effect-native agent execution kernel: sessions, runs, turns, steering, follow-ups and typed lifecycle events on top of Effect AI.

Monorepo-safrs★ 10

Agent-First Repository is a human-governed software environment designed so AI agents can execute engineering work efficiently while deterministic controls constrain their authority, verify their output, and preserve human accountability.

hybrid-rag★ 10

Production-grade hybrid RAG: BM25 + dense retrieval + cross-encoder reranking + LLM-as-Judge

RF-AIagent★ 10

AI-Agent driven RF design system with HFSS automation for antennas, filters and transmission lines

anima★ 10

Always-on AI agent with persistent long-term memory, sleep-time consolidation, and dreams — runs 24/7 on a small local LLM (Ollama, 2B params, zero dependencies)

ComfyUI-DirectorMaster★ 10

🎬 导演级 AI 影视创作 ComfyUI 节点包:600 位导演风格库 + 246 创作模式,一句话创意 → 剧本、分镜与 AIGC 镜头级提示词,直供 Seedance/Wan 等视频模型 | Director-grade AI filmmaking nodes for ComfyUI: 600-director engine, idea → script → storyboard → AIGC-ready shot prompts

mxmon★ 10

Sudoless system monitor for Apple Silicon: power, thermals and per-process watts, in a terminal UI and as a JSON contract that scripts and AI agents can query

Astera★ 10

Desktop app for running and orchestrating many Claude Code and Codex sessions — account rolling on usage limits, git worktree isolation, and Slack remote control.

GeeLo★ 10

用 AI 开发 GEE 的免干预工作流:AI 写完 GEE 脚本后自己在本机连真服务器跑、看反馈、自己改,调通了再交付。适配 Claude Code / Codex / Cursor / Gemini CLI 等主流 AI 工具。

octet★ 10

fast rust coding agent, extensible in any language, multimodal inputs, deep provider integrations.

HakoVM★ 10

HakoVM: Firecracker-class microVMs for macOS, built for AI agents. One binary on Apple's Containerization framework.

unveil★ 10

Find text that hides from humans but speaks to machines. Defensive scanner for indirect prompt injection in untrusted content.

skill-doctor★ 10

🩺 A GitHub Action to validate Agent Skills against the official specification with helpful diagnostics

tender-master★ 10

可供 coding agent 调用的标准化招投标编制 Skill + Agent:九步流程、评分镜像目录、风控隔离、五专家评审、DOCX 一键整合,含监测/测绘两个完整样例

trip-planner★ 10

国内风景路线 AI 行程规划 Skill(Codex/Claude/Cursor 通用):航班核验→高德实测路线→携程+飞猪房价→点评+美团餐厅→Markdown+PDF 攻略

dotty-tutor★ 10

AI 教材数字化与互动辅导平台:PDF/扫描教材经 MinerU OCR 结构化出题,文本 + 视觉双模型审校与确定性质量门禁;学生端七种题型互动、分层提示与错题多轮陪练闭环;FastAPI + PostgreSQL JSONB + React 19

dsh-android★ 10

把 DeepSeek Harness 的 host 和 client 一起装进 Android 手机:不连服务器、不依赖另一台电脑。非官方项目,不上架,GitHub 直发 apk。

eveil★ 10

Self-hosted cold outreach agent. Give it your product's URL: it finds companies that fit, finds the people, writes the sequence and sends it from your own mailbox over SMTP. No purchased lists, no tracking pixel, no warm-up. AGPL-3.0, Docker.

hermes-agent-vs-code★ 10

Hermes Agent chat sidebar for VS Code — editor-aware context, workspace file references, skills, sessions, and approval modes.

TravelBrain-Multi-Agent-AI-Travel-Planner★ 10

TravelBrain is a multi-agent AI travel planning system that works together to create personalized, efficient, and complete travel plans based on the user’s preferences, budget, and schedule. It can coordinate different agents for destinations, transportation, accommodation, activities, and itinerary planning to deliver a seamless travel experience.

meelu-analytics-mcp★ 10

Ask your AI assistant real questions about your data and get answers you can rely on — an MCP server with 45 analysis tools that pick the right statistical method themselves and tell you how much to trust the result.

larksuite-oapi-sdk-rs★ 10

Rust SDK for Lark / Feishu (飞书) Open Platform APIs, bots, events, WebSockets, and interactive cards.

Awesome-OKF★ 10

OKF (Open Knowledge Format) — curated catalog of tools, plugins, skills, proposals, and docs for agent-friendly knowledge. YAML-driven, agent-searchable, MCP-ready.

ken★ 10

Thompson-mode systems discipline for AI agents. Think first, build bottom-up, brute force until measured, rewrite over patch.

itqan-engineering★ 10

Itqan (إتقان — mastery of the craft): a model-agnostic AI engineering skills suite that runs the full software-engineering lifecycle. 12 skills — a resumable orchestrator plus six phases and five specialists. Approval gates before code, test-first builds, evidence before done.

sdlc-graph-engineering★ 10

Turn any multi-step process into a guarded graph a machine can actually execute — typed nodes, total exit guards, bounded retry loops, durable run state, and a ledger of every step that could not run. A Claude Code plugin.

Flydb★ 10

给开发、运维和 AI Agent 的数据库迁移工具:CLI + 本机 GUI,共用配置、预览与执行记录;覆盖主流与国产数据库,Java 8 零依赖内核。

fun★ 10

A lightweight, embeddable, data-centric scripting language whose reach extends from JSON/FD data all the way down to runtime-compiled C and raw machine code.

notifyd★ 10

Agent-first notification service in Rust. Email, SMS, push, in-app inbox. One binary, Postgres only, MCP server built in.

memorybridge★ 10

Award 1 winner in Agents for Good — safety-first multi-agent dementia care support prototype built with Google ADK, MCP, Cloud Run, and human approval.

AgentSeat★ 10

Lightweight Wayland scaffold for AI agents to operate one GUI app without stealing the human's host focus, cursor, workspace, or clipboard.

Monozukuri★ 10

An AI coding skill that applies Japanese-inspired craftsmanship to build simple, correct, verifiable, and maintainable software.

memory_and_context_eval_harness★ 10

Open evaluation harness for AI agent memory systems. Runs LoCoMo and LongMemEval against Synap, Mem0, Zep and Supermemory with pluggable provider adapters.

behavioral★ 10

Behavioral agent harness — a neuro-symbolic, self-improving agent built on the behavioral-programming runtime.

firefight★ 10

Open-source AI SRE and incident management. Finds the root cause and fixes it.

bufatechno-webgamedev★ 10

SKILL FOR MAKE GAMES WEB BASED

awesome-agent-protocols★ 10

A curated list of protocols and standards for AI agents — MCP, A2A, ACP, AG-UI, AP2, x402, and 50+ more, organized by stack layer

ios-reverse-skills★ 10

Multi-LLM iOS reverse-engineering toolkit. 10-phase workflow with adapters for Claude Opus/Code, Cursor, Qwen Coder, MiniMax, Codex/GPT-5, Aider, Cline. Adapted from incogbyte/iOS-reverse-engineering-claude-skill (Unlicense).

video-watch-mcp★ 10

Let AI agents watch videos — cloud-hosted MCP server with transcript + frame extraction for TikTok, YouTube, and 1000+ platforms

ResearchPilot-Skills★ 10

9 AI agent skills for academic research — evidence search, citation validation, literature expansion. Works with Claude Code, Codex, Gemini CLI. Free API tier included (OpenAlex, CrossRef).

agents-md★ 10

Generate and safely maintain AGENTS.md, the cross-tool standard for AI coding agents. Non-destructive re-runs, never fabricates, three-tier boundaries.

agential-skill★ 10

A cross-platform skill that makes AI coding agents generate minimal, editorial-grade frontend UI instead of generic SaaS templates.

obsidian-tc★ 10

Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. Multi-vault native, pluggable embeddings, OAuth-ready HTTP. TypeScript + Rust. AGPL-3.0-only.

skilly★ 10

Enterprise-grade, self-hosted registry for governing SKILL.md agent skills, with identity anchored in Microsoft Entra ID

subroutine★ 10

A self-hosted, agent-native task and decision tracker for people and coding agents working on complex projects. Install it, tell Claude "we use Subroutine now", and you never type a ticket.

popcorn-oss★ 10

Self-hostable browser runtime infrastructure for agents.

1c-ai-pipeline-rules★ 10

Промпты и регламент конвейера из семи ИИ-агентов: от постановки до боевой базы 1С

Zelyq★ 10

Open-source AI app builder. Describe an app, watch an agent build it in a real workspace, and edit the result live — on your laptop or your own cloud.

wechat-video-subtitle★ 10

下载微信视频号普通视频、直播回放并转写逐字稿的 AI Agent Skill

Aether-Agent★ 10

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

opencode-loop-plugin★ 10

OpenCode loop plugin for Claude Code-style /loop recurring prompts, idle-aware scheduling, dynamic pacing, and AI coding agent automation.

antigravity-move-chat-to-projects★ 10

Lightweight CLI tool to move and transplant Google Antigravity conversations, trajectory steps, and artifacts between workspaces.

opusclip-mcp★ 10

OpusClip MCP — turn long videos into AI-curated short clips, from your agent. Hosted (remote) MCP server.

agent-playbooks★ 10

Portable engineering workflows for AI coding agents — 35 playbooks for bug fixing, feature development, code review, testing, and security, across Claude Code, Cursor, Codex, Copilot, and more.

agent-hitch★ 10

The execution layer for model and harness evaluation.

agent-harness★ 10

Adapter-driven control plane for coding-agent work: tasks, goals, run DAGs, gates, verification, and state sync.

web-scraping-mcp★ 10

MCP server for HasData's Web Scraping API: fetch any public URL through managed proxies, render JavaScript when needed, and get markdown, text, HTML or structured JSON. From 1 credit a call.

yelp-mcp★ 10

MCP server for Yelp: business search, place details and the full review feed as JSON. Hosted, no Yelp Fusion key. 1,000 free credits every month.

mio-chat-frontend★ 10

🖥️ MioChat 前端 — 基于 Vue 3 + Element Plus 的沉浸式 Agent 交互界面:多 Agent 群组、Artifacts 画板、工具管理与会话可视化。

ollama-chat-application★ 10

A production-ready conversational AI app powered by Chainlit and Ollama, with multi-modal document processing, MCP tool integration, and persistent chat sessions. Handles voice input, file analysis (PDF, DOCX, images), and dynamic LLM switching via customizable chat profiles. Easily deployable on Railway for fast, scalable cloud hosting

vapi-studio★ 10

Open Source & Free tools for VAPI

agentur-agent★ 10

Agentur’a — multi-chat AI agent with per-chat memory.

rag-eval-workflow★ 10

A framework-neutral RAG evaluation skill with golden sets, regression gates, and script-domain checks.

neo-agent-brain★ 10

Point a cross-model AI engineering team at your own codebases. The Agent OS keeps named AI maintainers' identity, memory and review across labs alive between sessions — the Brain Neo.mjs runs on itself. Multi-tenant: onboarding a codebase is a config entry, not a fork.

walmart-mcp★ 10

MCP server for Walmart: keyword and category search, product pages with the buy box and other sellers, and the review feed with its filter block. 1,000 free credits every month.

dsh-zhihu-search★ 10

DSH 插件:基于知乎开放平台官方 API 创建的站内搜索、全网索引搜索与直答三个工具。搜索不幻觉,引用有出处。(原生嵌入“设置-插件-插件配置”)

causadb★ 10

Memoria del proyecto para agentes de IA, cambiá de agente sin perder la historia.

android-claude-agent★ 10

AI Agent 免 Root 免电脑永久控制 Android — 无线调试做跳板,adb tcpip 5555伪装USB模式,127.0.0.1回环自连

TeleDOM★ 10

⚡ Temporal Browser Intelligence & Agent-Owned Workflow Runtime with 350 Certified MCP Tools & Python SDK · Sub-Millisecond DOM Time-Travel, Target Memory & Deterministic Automation.

neo-agent-skills★ 10

Install the workflow substrate a cross-model AI team actually runs on: ticket intake, PR review gates, lane coordination and guards, versioned as a package. The skills Neo.mjs maintainers load every session — materialized into your repo, not copied.

terminal-mcp★ 10

An MCP server that gives LLMs a real interactive PTY with observability and seamless human takeover.

agent★ 10

Server-side agent runtime in TypeScript — streaming chat, tool calling, knowledge-base retrieval, and answers with citations. Ships with a web app and an admin console.

openclaw-soft-engine★ 10

🦞 Industrial-grade Soft Execution Engine for OpenClaw. Features Multi-Expert Routing (DeepSeek-R1/V3), DAG Scheduling, API Key Pooling, and Docker Sandbox isolation.

Qraft★ 10

Qraft · 题构 — 开源算法题创作工作区,支持 AI 出题、混合题集、题库组卷与 Windows 桌面客户端。

looms★ 10

TypeScript SDK for durable agents, workflows, and custom execution kinds. Built by Swirls.

openapi-llm-wiki★ 10

📚 LLM Wiki — A structured knowledge repository designed for LLMs and AI agents, containing authoritative documentation for the @openapi® API marketplace.

academic-agent-toolkit★ 10

250+ academic Agent skills + orchestration engine: math modeling · paper writing · LaTeX · scientific figures · literature review · IP drafting. Host-agnostic (any Agent), quality gates + audit evidence chain. CC-BY-NC-4.0.

agent-skills★ 10

A curated collection of reusable agent skills for design, research, browser automation, and developer tooling.

temporal_reasoning★ 10

Perfect memory. Exact reasoning. Complete history for AI agents.

instantcms-mcp★ 10

MCP server for InstantCMS 2: 101 tools, source-backed API knowledge, runtime-verified generators. MCP-сервер и AI-workflows для разработки под InstantCMS 2.

easy-unlocker★ 10

Secrets management for AI agents: approve API keys and credentials on your phone with biometrics, delivered end-to-end encrypted into the target process. Plaintext never enters the chat, logs, or relay.

auditable-memory-records★ 10

Auditable Memory Records (AMR) — a small specification for provenance and epistemic status in agent memory. Draft 0.1, seeking implementers.

Token-Terminator★ 10

Agent-agnostic JEV-enabled token reduction with exact recovery and fail-open guarantees. First-party Hermes Agent Context Engine; RTK terminal rewriting optional.

causalmesh★ 10

MCP server that gives your AI coding agent a map of your polyglot codebase — reverse dependencies, gRPC tracing, event/topic flows, and doc search, without burning context. Single local Rust binary, no network calls.

tcm-ai-skill-hub★ 10

TCM AI Skill Hub|一次安装 7 个公开中医 AI Skill,按学习任务自动选用、按来源回答。

tapl★ 10

A durable workflow harness for Codex.

Browse other framework pages