Custom agents

Atlan AI Agent Toolkit

BoringOS is the open-source operating system for AI agents - it ships with a shell portal plus installable modules, powered by agentic CLIs.

TMLR | This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms.

Autonomous research harness for AI agents. Give it a measurable goal — it hypothesizes, experiments, and iterates until it finds a solution or tells you what it learned.

A framework-agnostic UI kit of production-ready components for building AI and LLM chat interfaces.

An agentic system for autonomously generating explainable and reproducible time-series anomaly detection rules using LLMs.

Use Claude Code Agent Teams inside Zellij — a tmux shim that translates tmux commands to zellij actions

RLVR training for LLM in CUDA/C++

Claude Skills For Sales Optimization

Solana meme-coin auto-trading bot with MiniMax M2.7 LLM exit advisor, Jupiter Ultra swaps, Telegram control, and a Pepe-on-Moon dashboard

AI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and supports Gemini, Claude, Cursor, and Copilot.

Agent Interface Compiler — One command. Every agent speaks your product. Transform OpenAPI specs into MCP Servers, Skills, CLAUDE.md, AGENTS.md, and more.

Your codebase's journey, narrated by agents - Orchestrate AI agents across issues, profiles, and machines. Full visibility from dispatch to PR.

[AAAI 2026] LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

WORKBank Database derived from large-scale audit of worker desire and technological capability of AI agents for work.

Open-source AI agent social network built with Next.js + Supabase. Self-hostable, cryptographically secure, API-first. MIT license.

Open-source alternative to Granola and NotebookLM. Records meetings without a bot, transcribes locally with Whisper, and lets you chat with your notes using any LLM or Ollama. Your data stays on your machine.

Providing a strong Gravity (sandbox) in the wild world of AI Agents (Antigravity, claude code, ...), to preserve the developer's Sanity.

Exercises for the Agentic RAG live course for O'Reilly.

Runtime provenance for AI and scientific workflows—capture, enrich, and query workflow data via observability adapters and code annotation across edge, cloud, and HPC.

AI-native Lexical rich text editor. Edit, render, SSR, and AI agent protocol (LiteXML) — all from one schema. React 19, TypeScript, Vanilla Extract, ESM.

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

Curated list of papers, frameworks, benchmarks, and applications for multimodal AI agents (LLMs, text-to-image, speech, world models, etc.) on mobile and edge devices.

Give your agents a cute office. Multi-device, multi-user, multi-agent collaboration.

Multi-agent architecture for Opencode — cost-optimized model routing, parallel specialist execution, dev tools, and a self-maintaining project wiki

Official Postman plugin for Claude Code

Transform AI agents into orchestrating assistants managing calendars, contacts, and tasks

Ghost personas review your code before it ships. Find edge cases, race conditions, and business logic bugs before production.

Swarm — Autonomous Drone Navigation

Free, open-source AI coding agent for terminal and browser. A Claude Code / Cursor alternative that runs offline with Ollama or with your own Claude, GPT or Gemini keys. No account, no subscription. 🇮🇳

A curated list of 474 AI tools, agents, MCP servers, and resources for DevOps, SRE, and Platform Engineering — updated July 2026

WormGPT CLI V2.0 is here but is still in the development stage from the previous version which I did not optimize for its function, please be patient and calm!.

Kimi for Claude Code, Codex, and DeepSeek Harness: code questions, independent reviews, bounded fixes, autonomous goals, parallel tasks, and MCP tools through your local Kimi Code CLI. Available through GitHub marketplaces and npm.

Java-based Enterprise AI Harness — AI-powered automation platform built in pure Java on Abundent's fork of the Play Framework 1.x with a Nuxt frontend. Combines agent orchestration and job scheduling with no Spring, no Node.js, and no Python runtime.

Manvo TV — 想到什么就生成什么 · AI 原生创作平台(无限画布 + 漫剧剧本工厂) | https://manvo.tv

An Agent Skill for Claude Code, Codex and other coding agents: train on rented GPUs without losing checkpoints or paying for idle machines.

Rules, regulations, disclaimers and similar documentation for Agents League @AISF 2026

Portable AI agent skills for private career context, local VitaeGraph records, and evidence-based career work across GitHub, LinkedIn, CV/ATS, portfolios, and X.

Open-source legal AI agent skills for PKULaw, citations, and DOCX workflows

AI 简历优化工作台 · 多 Agent 协作 · 把简历和 JD 变成 30 秒可执行的优化建议

Local-first static analysis that turns source code into deterministic, source-grounded workflow maps for coding agents via MCP.

VS Code-style typewriter animation video skill for AI agents (agentskills.io format)

A free, living knowledge base on vibe coding — building SaaS fast with AI agents, local AI, and agentic workflows.

Official Repository for our paper: PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems

Custom translators for Linguist browser extension

Curated Dify workflow DSL files and templates for RAG, agents, search, translation, deep research, SEO and automation.

A living literature repository for Token Economics for LLM Agents: A Dual-View Study from Computing and Economics.

Peek into your agents. Real-time visualization for multi-agent AI systems.

AI-driven toolkit that automates evaluation processes for AI agents

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

52 AI agents orchestrating complete SDLC with governance, cost optimization, and phase customization. Autonomous development from spec to production with human oversight.

Claude Code Research Harness Workflow turns Claude Code from a general coding agent into a controlled empirical research collaborator | by 朱晨 | 遗传社科研究

Full Stack Agentic App Builder with Next JS, Supabase, Gemini AI, Cline SDK, Shadcn UI Tutorial 🔥🔥

Swarm-first multi-agent messaging and task orchestration extension for Pi

CoDA is a multi-agent framework that turns natural language queries into publication-quality visualizations.

Claude Code plugin: AI agent for your Obsidian vault — process books, courses, papers, YouTube into connected notes

A prompt-aware LLM router that predicts which models can complete each request, then selects the cheapest capable one: 53.2% lower cost and +1.9 pts completion on our tested dataset.

Per-project semantic search over Claude Code session history. Indexes JSONL transcripts into SQLite; retrieves via bge-m3 embeddings (Ollama) with FTS5 fallback.

Landing page and hub repo for Workato Labs — an open-source developer toolkit for building, validating, visualizing, and managing Workato recipes with AI coding agents.

Agent Reference Stack for Kubernetes (kars) - an open source stack from Microsoft for running AI agents safely on Kubernetes. Multi-runtime, Foundry-aware, hardened per-agent sandboxes, governed egress, end-to-end encrypted inter-agent mesh.

An asynchronous file-based handoff protocol for Claude Code and Codex agents sharing one project workspace

Minimal runtime for long-running autonomous agent experiments

This is the code repository for the book "Microsoft Agent Framework in .NET: Build production-ready AI agents and multi-agent systems in C#", former "Building AI Agents in .NET" (Manning)

An open source agentic AI companion harness. Persistent identity, memory, adaptable to multiple interfaces. Many features, updated often, developer friendly.

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

Superpowers workflow skill pack adapted for Hermes Agent and ChatGPT

Opinionated AI-native monorepo starter — build your MVP as a production-ready structure. apps/services/libs · Tilt · Nx boundary-enforced · agent-ready.

First-principles Manim skill for Claude Code — mathematical animation from scratch, paper-explainer patterns, 21 rule files.

A native, performance-first ADE built with Flutter, Rust, and Ghostty. Run Claude Code, Codex, Amp, and other CLI coding agents in parallel. No Electron.

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

基于 Pydantic AI 框架构建的多Agent协作系统，实现了管理Agent与工作Agent的分工协作，支持百轮级别的工具调用，让AI真正具备处理复杂任务的能力。

An open experiment in memory for AI agents — the whole memory, always in context.

并发调用本机 Grok 4.5、Kimi K3 与 Claude Code，带实时心跳和独立日志 | Concurrent local model CLI orchestration with live progress and isolated logs.

AI agent's skills manager

A modern desktop IDE with AI-powered chat assistant, Monaco Editor, and integrated terminal.

Lead-magnet repo: skills, hook scripts, recipes, and prompts for orchestrating AI coding agents inside cmux. Free, MIT.

The visual layer of your agent harness. Renders React components and Three.js scenes from source, with structure and evidence behind every frame — so agents can see, verify, and fix what they built.

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

Better memory for your AI agents. (Karpathy + Graphify + PCKC)

Visualize installed Skills and symlink status across AI agents

GEZHI (格致): a scholar-centered agent architecture for traceable, reviewable, and verifiable empirical social-science research.

Agent-native long-term memory that learns after every run. File-native, auditable, and integrated with Pi, Hermes, OpenCode, and OpenClaw.

Turn judgments into decisions. Open-source decision engine in Rust for teams whose thresholds change often, live in many places, or move money. Jev reads the text, Ordo decides what happens next and shows which decisions change before you ship.

Practical reference for fleet engineering, governing populations of AI agents with accountability

AI agent skills for claude code that generates comprehensive wiki-style markdown document for codebase, with CI/CD-ready incremental updates

Memory database for AI agents — stores typed memories (facts, preferences, events, entities, relations) with provenance, confidence, and bi-temporal validity, and answers with fused semantic + lexical + entity-graph + temporal retrieval. One Rust core, one binary wire protocol. Apache-2.0.

Guest agent for Tart VMs

AI thinking indicators and a voice-agent orb for React Native and Expo. Six dotted loading animations plus an audio-reactive voice orb, on the UI thread with Skia + Reanimated. Port of Jakub Antalik's thinking-orbs.

AI驯剪 — AI 自动剪辑视频：转写/剪气口/语义动效自动初剪 + 可视化 AI 视频编辑器人工定剪，开源闭环 | AI rough-cut + human final-cut video editing system

🕸️ Engineer the organization, not just the agent. 620 curated resources · 9 design layers · 11 sections · 298 papers & preprints — a field guide, CC0 open dataset, and interactive atlas for graph-structured multi-agent systems: roles, topologies, handoffs, work graphs, state, gates, reliability, observability.

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM trading agents, with A-share data

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.

Open-source ADE for Claude Code, Codex, OpenCode, Cursor and more. Put several coding agents in one thread, with pull requests, a browser and Git beside the chat.

Local guardrails for coding agents. Policy, approvals, 86 safety packs, OS sandbox, audit trail — no Docker.

The goal of this blueprint is to develop an agentic AI workflow that provides insight to the end user on close-to-optimal configuration values for specific RAN parameters at a cell-site.

Papers about agentic AI geospatial data.

A focused Hermes profile for learning the agent without tool overload

Turn your logo into an animated thinking indicator for agent UIs and more.

Agent skills distilled from non-fiction books. Works with Claude Code, Codex, Gemini CLI, Cursor, Copilot, and 20+ platforms.