Catalogue

Tool

Terminal-Bench

QACoding

harbor-framework

Benchmark and harness for evaluating AI agents on end-to-end tasks in real terminal environments.

evaluationcliterminal-tasks

Tool

Aisuite

CodingInference

andrewyng

Simple, unified interface to multiple Generative AI providers

multi-providergatewaytool-callingagents-api

Tool

Chrome Agent

InterfaceQA

captivus

Open-source CLI that controls Chrome over the DevTools Protocol so agents can browse with a sense-act-verify loop instead of an MCP browser server.

browser-automationchromeclidebugging

Harness

ClawTeam-OpenClaw

Coding

win4r

ClawTeam fork where a leader agent spawns and coordinates CLI coding-agent workers in git worktrees, with OpenClaw as default

multi-agentgit-worktreetmuxtask-orchestration

Convos

Interface

Shared group-chat rooms where live agents and their human operators talk together

group-chatmulti-agent

App

Fox in the Box

InterfaceMemory

fox-in-the-box-ai

Self-hosted AI assistant bundling the Hermes agent, chat UI, local memory, and optional Tailscale remote access into one desktop app

ollamatailscalemem0local-first

Tool

Hermes for Home Assistant

VoiceConnectors

rusty4444

Bundle connecting Hermes Agent to Home Assistant with a custom integration, service-call tools, and an optional wake-word/STT/TTS voice loop

home-assistantwake-wordttsstt

Tool

LangMem

Memory

langchain-ai

Long-term memory toolkit for agents: hot-path memory tools, background consolidation, and LangGraph store integration

langchainlong-term-memory

Tool

LightMem

Memory

zjunlp

Agent memory has a hidden bill: the tokens and calls spent building and updating it, often more than answering the quest

raglong-term-memorytoken-optimizationlightweight

Framework

MCP-UI

Interface

MCP-UI-Org

Server/client SDK for embedding interactive UI resources in MCP tool responses; basis of the official MCP Apps extension.

sdkembeddable-ui

Harness

Mercury Agent

Interface

cosmicstack-labs

Permission-first personal AI agent with SQLite-backed memory and token budgets, run from CLI, web, or Telegram

clitelegramsqlitecron

Tool

Screenshot to Code

Coding

abi

Converts screenshots, mockups, and screen recordings into HTML, Tailwind, React, Vue, Bootstrap, or Ionic code

ui-generationtailwindmultimodalfigma

Tool

Shepherd

Coding

shepherd-agents

Records agent runs as reversible, inspectable execution traces whose outputs are reviewed before they are applied or discarded

sandboxagent-builderreversible-executionmeta-agent

Tool

Solo

CodingMemory

solo-agent

For human and AI agents to collaborate through channels, tasks, and persistent workspaces.

multi-agentcoding-agentlocal-firsttask-management

Harness

Weco CLI

Coding

WecoAI

Command-line agent that iteratively writes, evaluates and optimises code against a metric.

code-optimizationpromptcligpu-kernels

Tool

Activity Frames

MemoryData Wrangling

nossa-y

Episodic memory for AI agents. Records your screen locally, compiles it into structured activity frames, serves them over MCP. No cloud, no

episodic-memoryscreen-recordingcomputer-uselocal-first

Tool

Agent Skills

Coding

WordPress

Portable skill bundles teaching AI coding assistants WordPress block, theme, plugin, and REST API development patterns

wordpresscmsskill

Framework

Amazon Nova Act

InterfaceCoding

aws

Python SDK combining natural-language steps and code to build browser agents.

browser-automationcomputer-usehuman-in-the-loopcloud

Tool

Doc7

Data Wrangling

magicrew

Turn documents into AI-ready Markdown with visual understanding

document-processingocrvision-language-modelmarkdown

Harness

Headlong

MemoryConnectorsInterface

laude-institute

An open source agent microharness featuring persistent agency and recursive LLMs. Of bash, by bash, for bash; it's shells all the way down.

productivitypersistent-agencyrecursive-lmbashmulti-user

Harness

Maestro

Coding

ReinaMacCredy

Single-binary local store that keeps agent work as cards and tasks with proof and QA gates, all as files in the repo

local-firstproof-gatedtask-management

Tool

Numbat

SecurityMonitoring

perplexityai

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

endpoint-detectionforensicsgovernancetelemetry

Harness

OpenManus

InterfaceCoding

FoundationAgents

Open-source framework for building general AI agents with optional browser automation, from the MetaGPT community

browser-automationmulti-agentplaywright