Custom agents

Self-hostable execution engine for reliable, observable, tool-using AI agents — with custom orchestration, persistent memory, trace replay, automated evals, and MCP integration.

An experimental Application Object Model for helping LLM agents understand, reason about, and operate real apps.

Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.

The first open-source multi-tenant agent memory framework that works across any LLM combination with zero tokens per recall.

Research workrooms for AI agents: evidence retrieval, citation audit, adversarial review, peer review gates, and clean final reports.

Vectorless multi-agent research pipeline that transforms a raw topic into thematic structures, ranked gaps, competing methodologies, and a funding-ready proposal. Eliminates traditional RAG by using LLM-native synthesis with interpretable reasoning, quality gates, and quantitative novelty scoring.

Semantic, persistent knowledge graph memory for LLM-based and multi-agent systems, exposed via the Model Context Protocol (MCP).

Lightweight, thread-safe memory kernel for autonomous agents. Strengthens knowledge through reinforcement, prunes with gentle decay, and exports transparent Markdown — pure SQLite. Foundation for persistent, self-improving reasoning.

LLM agent that automates DAG-based ML pipeline migration - from config parsing to pull request

Hybrid RAG (BM25 + NumPy in-memory vector store) with LLM-as-a-Judge response scoring and a retrieval evaluation harness. Built with Gemini 2.5 Flash.

Provider-agnostic runtime for multi-agent LLM systems: declarative agents, cross-provider routing, pluggable memory, FastAPI + WebSocket observability.

Multi-agent Smart Contract Security Audit Pipeline — 5 specialized AI agents for vulnerability scanning, logic auditing, gas analysis, compliance checking, and report generation. Powered by MiMo.

Multi-agent AI workflow platform — coordinator-driven, 11 agents, 227 skills, 15 rules.

Fugue — many agents, one spec. Claude as CEO/orchestrator, Codex CLI as worker fleet, specs as the design doc: an anti-drift multi-agent engineering harness.

Agent Team & Skill Architect for Claude Code (Simplified Chinese) — 面向 Claude Code 的简体中文元技能，一句话自动生成多智能体团队与技能

HIVE is a multi-agent orchestration system built on top of Hermes Agent. Describe what you want in one sentence, and HIVE handles the rest: requirements translation, task decomposition, coding, testing, review, and packaging — with support for iterative refinement.

Open-Source Scout is a multi-agent AI system that helps beginners contribute to GitHub projects by automatically ranking beginner-friendly issues, locating relevant code, and generating fix plans and pull-request drafts.

Loop Engineering for AI coding agents, with real review boundaries. Your AI reviewer cannot edit code. Structurally.

Autonomous multi-agent system for discovering, entering, and winning Kaggle competitions

Autonomous AI coding agents for long-term task execution.

Terminal UI for BoJ local-coord-mcp — peer discovery, task coordination, and window titling for multi-instance AI sessions

Multi-agent coding OS — BMad pipelines, Karpathy wiki, closed learning loops, dual-runtime coordination (Claude + Codex)

PIV Loop SDK: typed Plan/Implement/Validate agent framework for Claude Code, with independent validation loops and a full test + benchmark suite.

a multi-agent workflow orchestration platform

Let multiple Claude Code CLI sessions talk to each other — a tmux-based message broker that routes messages between agents over MCP.

Multi-agent LLM orchestration: a supervisor decomposes tasks, specialist agents run tools in parallel across distributed workers, with human-in-the-loop review, long-term memory, and OpenTelemetry observability.

Make sure AI agents actually do what they claim, no more fake successes.

Source-available local multi-agent engine for smart-contract security review and defensive ECC research with reproducible evidence. FSL-1.1-ALv2.

多Agent工作流验证版本

Ask one question to multiple AIs — they debate each other and you get one unified answer. macOS desktop app.

Offline prompt evolution engine for multi-agent systems, benchmark suites, and inspectable prompt DNA.

Multi-agent orchestration desktop app · 4 collaboration modes (Roundtable / Pipeline / Debate / Freeform) · Tauri + React + Rust

双 Pipeline 多 Agent 协作框架 PM + 6 个 Agent + 5 道关口 = 不会悄无声息挂掉的代码。可用于：Claude Code, Copilot, Cursor, Windsurf.

DesireCore Documentations.

Verifiable Codex + Claude + Gemini collaboration framework with source checks, mutual cross-audit, merge gates, HTTP and MCP adapters.

Multi-runtime agent framework (Claude Code, Codex, Antigravity) with hard/soft controls, audit-first hooks, and multi-dev coordination.

Arbiter — Agent Runtime · Agent 运行时。上下文管理、配额调度、熔断器、审计轨迹。开源免费。pip install 即用。

Historical standalone Agentic repository. Active development moved to pyfly.agentic in pyfly v26.10.08. See native documentation and migration guide.

NexQuant is an autonomous AI agent for quantitative strategy research. Built on a multi-agent framework

多 AI 智能体协作开发的桌面工作台 把并发的 AI 团队管理得像发 IM 一样自然

Experimental Python Trust Kernel for agent interoperability, authorization, budgets, durable governance and verifiable evidence. Bounded protocol support; production qualification pending.

M4STCLAW v3 — MCP-native autonomous AI mesh network with multi-provider routing, failover, memory, and task automation.

Free, open-source, self-hosted social AI companions with browser chat, memory, personas, and optional Second Life, OpenSimulator, and Discord bridges.

Open-source rollout, verification, and trajectory plane for agentic reinforcement learning.

Cross-agent prompt pocket: remember your most-used prompts and pick one to run. Works on Claude Code, Codex, OpenCode, Cursor, Copilot & Gemini; auto-scans Claude/Codex/OpenCode sessions for prompts you repeat 7+ times. Forged by agent-plugin-kit.

Make agentic coding work on real codebases. DevFlow is a Claude Code plugin that turns a request into a complete, tested, reviewed, documented pull request that's ready for your final review, and improves itself weekly.

Agent-first CLI for driving mobile apps via Appium

Vue 3 native bindings for CopilotKit — the full-stack SDK for agentic apps, Generative UI, and chat.

app for coding agents

Kit do time em Português (BR) — workshop de modernização de Natural/Adabas com GitHub Copilot e Spec-Kit

Battle-tested AI interaction frameworks, philosophical archetypes, and context engineering patterns. From the team behind Stackbilt.

An agentic, zero‑shot document intelligence engine that sees, understands, and extracts from any PDF, no training, no hallucinations. Just define your fields and get trusted, structured outputs with confidence scores, deployed locally and built for the enterprise.

SAP ATC Checker - Run ABAP Test Cockpit checks with any check variant via SAP ADT API

Another OpenClaw alternative

✨🧠🤖 A low-code AgenticOps workflow based on n8n, MCP and Cisco RADKit for some nice Network Automation experiments

Ship code while you sleep. Open-source CLI that orchestrates autonomous coding agents with Docker isolation, git worktree safety, and a review workflow.

VELLA = Verifiable Evidence Ledger & Logic Authority; deterministic pre-execution authorization and signed proof for AI agents and automated workflows.

An AI-powered life management system. Free and busy.

Documentation for the Ejentum Reasoning Harness. Guides, API reference, and concepts for the RA²R methodology and the Ejentum API.

strangeClaw is a minimal, self-hosted autonomous AI agent with full Firecracker sandbox isolation support.

Open-source ADR orchestrator — explores your codebase, proposes approaches, writes Architecture Decision Records automatically

Building production-ready agentic systems for financial data entry

Local-first Harness Operating System for defining, evaluating, evolving, versioning, and deploying agent harnesses.

Benchmark methodology, task sets, and evaluation results for RA²R

A fully local, multi-agent AIOS with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing built for the India Agentic AI Open Hackathon 2026.

The Autonomous Systems Platform — safety-first language, verification, simulation, readiness, assurance, and diagnosis for mission-critical robots, IoT, and edge systems.

A/B evaluate any LLM task with and without Ejentum cognitive injection. n8n workflow + TypeScript module.

Agentic exporter and runner for internal network pentesting, autonomous host discovery, patch/vulnerability state collection, and server/application inventory, surfaced as structured findings for the Lorikeet Security platform.

Agentic ai based retail analytics dashboard

A lightweight coding agent for teaching, research, and experimentation

Full Form : Expert Network for Intelligent Guidance and Multi-task Assistance. Using multiple LLMs, for Conversational as well as Functional Request.

1 prompt 1 product

Agentic workflow sandbox tailored for research tasks

Standard for authoring and deploying agents and workflows.

A powerful command-line interface for the Apollo.io API, designed for both humans and AI agents.

F5 for your filesystem: checkpoint before every agent command, restore even after rm -rf

Multi-agent synthetic-audience evaluation — parallel eval agents that score content and code before ship

GridVibe is a browser-first workspace for launching and managing multiple SSH terminals, local shell panes, agent panes, and SSH/SFTP or local repository file explorer panes from one control surface.

Agentic-first task management service. Plain text API, agent-driven, single Go binary with JSON file storage.

Lint and score any AI agent SKILL.md against the official Claude, Codex, and Antigravity authoring guides — offline Dart CLI.

Agentic, build-validated C# code examples for Aspose.BarCode for .NET covering barcode generation, recognition, and configuration across 60+ symbology's. Includes an agents.md guide for AI coding agents.

Agentic development framework for Claude Code, OpenCode, Codex CLI and Kiro — multi-runtime support

Let AI agents run, test, and debug inside your Okteto dev environments

Agents and humans live adjacently.

Moved to GitLab: https://gitlab.com/bithuman (this GitHub copy is archived, read-only)

smart terminal buddy: hey to ask, hey wtf to fix

Customizable AI Telegram bot starter kit powered by Google Gemini — multimodal, self-hosted, Telegram Stars payments, Adsgram integration.

💫 Visual data pipelines with AI-reviewed transformations and live spreadsheet output, built offline-first with Polars and PySide6.

🚀 AI development accelerator toolkit - Boost efficiency by 50-100% for Claude Code, Cursor, Copilot and more

Desktop home base for long-running AI agents. Powered by OpenClaw, vLLM, NVIDIA Parakeet STT, NVIDIA Magpie TTS, and MemPalace spatial memory.

An AI-assisted security testing workspace for authorized engagements.

A open-source, calm, local-first macOS Markdown reader for rich reading, connected notes, and private AI-assisted workflows.

A *Claw clone that utilizes BeamAgent to allow for TOS compliant subscription based account usage. A cautionary tale proving that technical adherence to the letter of a request is the most effective way to subvert its intended restrictions. "Be careful what you wish for..."

Revolutionising traditional survey methods by integrating conversational AI capabilities into a web-based survey interface. This interface will not only collect responses but also interact dynamically with respondents, providing a more engaging and personalised experience.

The Student Tracking System is an AI-powered platform designed for educational institutions, providing features such as personalized dashboards, attendance tracking, class management, and real-time updates. It enhances both student and teacher experiences with smart recommendations and an AI chatbot assistant.

AI-powered WhatsApp automation platform for coaching institutes. Automates student queries, admissions, and lead management.

Provide token-efficient, distilled QA docs for AI coding agents to generate accurate test code quickly and reduce token usage significantly

Artificial Intelligence-Yearning Fulfilment Unit

Flavor Bot is a recipe recommendation chatbot that suggests recipes based on ingredients or dish preferences.