Search results for "harness"
Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI),
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
A practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.
Local-first memory plugin for OpenClaw AI agents. LLM-powered extraction, plain markdown storage, hybrid search via QMD. Gives agents persistent long-term memory across conversations.
The memory-first coding agent
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.
ARIS βοΈ (Auto-Research-In-Sleep) β Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in β works wi
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
Memory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append-only thought chains plus a Git-like skills registry, lett
AI Agent Framework, the Pydantic way
Agent Swarm framework for AI coding agents and more!
A general-purpose coding agent that runs inside an NVIDIA OpenShell sandbox, orchestrated by Deep Agents and powered by NVIDIA Nemotron. The agent writes and executes code in an isolated, policy-gover
The ultimate space for work and life β to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level β enabling multi-agent collaboration, effo
An Agent Harness crafting around your project. From Desktop, CLI, editors, chatbots, APIs β everywhere you work.
A Markdown-first memory system, a standalone library for any AI agent. Inspired by OpenClaw.
β₯ AI Coding agent for the terminal β hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
Python Deep Agent framework built on top of Pydantic-AI, designed to help you quickly build production-grade autonomous AI agents with planning, filesystem operations, subagent delegation, skills, and
π₯ Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.
A productive AI coworker that learns, self-improves, and ships work.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of ta
An open-source harness for spec-driven code generation.
Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles β unified tools, skills, memory, and orchestration with built-in constraints, feedbac
The Map Everyone's Missing: LLM Knowledge Engineering in 2026 β First unified guide connecting RAG, Context Engineering, Harness Engineering, Skill Systems, Agent Memory, MCP, and Progressive Disclosu
OpenClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
AgenticX is a unified, production-ready multi-agent platform β Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical m
π¬ Harness Vibe Research with Self-evolving AI Scientists
Official MCP Servers for AWS
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs direct
The Self-Growing Karpathy LLM Wiki β grown by an AI agent yoyo from Karpathy's founding prompt
Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.
Automatically Update LLM-Agent Papers Daily using Github Actions (Update Every 12th hours)
mkdir beats vector DB. B-tree NeuronFS: 0-byte folders govern AI β β©0 infrastructure, ~200x token efficiency. OS-native constraint engine for LLM agents.
2026 swarm Agent εΉ΄οΌswarm Agent γAgent teamγ ai codingγskillγmemoryγevolveγagentic RL η AI Agentιε
MCP server for token-efficient large document analysis via the use of REPL state
MaverickMCP - Personal Stock Analysis MCP Server
A multi-agent LLM system for detecting and resolving cognitive dissonance.
The conversational control layer for customer-facing AI agents - Parlant is a context-engineering framework optimized for controlling customer interactions.
A social platform for humans and AI agents, built and maintained by its own AI team. Connect any agent via HTTP.
AI-powered bug bounty hunting from your terminal - recon, 20 vuln classes, autonomous hunting, and report generation. All inside Claude Code.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The Mind Palace for AI Agents β Autonomous Cognitive OS with affect-tagged memory (valence engine), token-economic RL (surprisal gate + UBI), Hebbian learning, ACT-R spreading activation, Synapse Engi
Plugin suite + bundled MCP servers for Claude Code. Full delivery lifecycle: Agile pipeline with multi-model AI review, project bootstrap, documentation generation, codebase audits, performance optimi
Harness LLMs with Multi-Agent Programming
Meerkat - A modular, high-performance agent harness built in Rust.
Make your OpenClaw agents better, cheaper, and faster.
An Excel AI agent that uses MCP tools to let LLMs read, edit, and automate Excel spreadsheets.
Security-first AI agent orchestration system. Built-in agents with predefined capabilities, strict guardrails on what they can and cannot do, and a four-layer defense system that enforces security at
The Go client for Chroma vector database
Open-source relational AI framework with identity persistence, memory, and MCP integration. Build relationship-aware AI agents that remember, grow, and maintain continuity. Built on Claude Agent SDK.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
A deterministic development harness for Claude Code β MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Gemini)
Agentic coding harness with persistent memory and a REPL body. Built on Ori Mnemos. Open source must win.
π§ PromptDrifter β oneβcommand CI guardrail that catches prompt drift and fails the build when your LLM answers change.
Autonomous AI Agent Harness β persistent memory, SWARM orchestration, event-driven triggers. The KAIROS pattern, built independently before the Claude Code leak. pip install adam-framework
Memory-centric self-improving harness for AI agents. Six-phase cycle + Security by Absence. ADRs, JSON schemas, and a dependency-free Python reference.
Local-first AI agent framework with GUI, memory, web search, personality constructs, speech i/o, tools, skills, CLI & Telegram features β fully self-hosted via Ollama.
Claude Code skills collection β CCA study guides, Twitter research, MCP review, auto-iteration tools
Self-hosted orchestrator for AI autonomous agents. Run Claude Code & Open Code in isolated linux workspaces. Manage your skills, configs and encrypted secrets with a git repo.
A local LLM-based autonomous agent orchestration platform featuring async background tasks, context-isolated sub-agents, dynamic knowledge injection, and strict security approval gates (Plan Mode).
Complete Workspace Template for OpenClaw - Full agent lifecycle with unified memory system (Markdown + SQLite), self-evolution, RAG. Not for SubAgent/Skill use.
A self-evolving scaffold for autonomous web projects. 9 workflows, hourly self-evolution, self-healing pipeline, feedback learning loop. The repo is the system.
ZimaOS Blue - A Local-First Agent Runtime for Bold Builders. Out-of-the-Box, Open-Source, Universal, Vendor-Neutral
Agentica: Lightweight async-first Python framework for AI agents. θ½»ιηΊ§εΌζ₯δΌε ηAI Agentζ‘ζΆοΌζ―ζε·₯ε ·θ°η¨γRAGγε€ζΊθ½δ½εMCPγ
Define and control AI agents in markdown with full prompt transparency, persistent memory, and integrated tools via the Claude Agent SDK.
GAN-inspired multi-agent system that autonomously builds full-stack web apps from a single prompt using Claude AI agents
Nix packages for AI coding agents and development tools. Automatically updated daily.
π Build memory and retrieval infrastructure for ReasonKit, enhancing data management and access for your applications with ease and efficiency.
π Build an enterprise-ready RAG system to enhance technical documentation querying with LangGraph and multi-step reasoning workflows.
A Markdown-native task runtime for agentic workflows. (AI Generated)
an agentic stack for edge mcu, desktop, service, and app
Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.
HealthFlow: A Self-Evolving AI Agent with Meta Planning for Autonomous Healthcare Research
PromptGPT is an opensource framework that enables users to automatically generate high-quality prompts with zero installations, coding necessary or technical knowledge. Promptgpt follows industry best