Catalogue

Harness

Weco CLI

Coding

WecoAI

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

code-optimizationpromptcligpu-kernels

Framework

Amazon Nova Act

InterfaceCoding

aws

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

browser-automationcomputer-usehuman-in-the-loopcloud

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

Tool

Numbat

SecurityMonitoring

perplexityai

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

endpoint-detectionforensicsgovernancetelemetry

Tool

UI-TARS-desktop

Interface

bytedance

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

multimodalbytedancecomputer-use

Tool

Adrian

SecurityMonitoring

secureagentics

Say your agent starts resetting passwords it shouldn't. Logging it after the fact is too late, and no prompt-injection c

prompt-injectionruntime-securitythreat-detectionpolicy-drift

Tool

DeepTeam

Security

confident-ai

DeepTeam is a framework to red team LLMs and AI agents.

red-teamprompt-injectionguardrails

Tool

Scorable

QAMonitoring

root-signals

Evaluation platform (formerly Root Signals) exposing judges and evaluators to agents via SDK and MCP for in-loop quality scoring.

evaluationsdk

Platform

Container use

CodingSecurity

dagger

MCP server giving each coding agent an isolated container and git branch so multiple agents work in parallel without clobbering each other.

daggersandboxdockergit-branching

Tool

Deepsec

Security

vercel-labs

deepsec from Vercel runs security review as a pipeline that grades its own output. A free regex pass marks candidate fil

vulnerability-scannercode-review

Tool

Grok Build

CodingInterface

xai-org

SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.

coding-agentcliacpsearch

Platform

Together AI

InferenceTrainingDeployment

togethercomputer

Inference, fine-tuning and GPU-cluster platform serving open-weight models.

gpu-clusterfine-tuneapisdk

Tool

BrainDB

Memory

dimknaf

Postgres and pgvector long-term memory for LLM agents with typed entities, graph traversal, temporal decay, and a REST API

postgrespgvectorknowledge-graphtemporal-decay

Tool

Drawio MCP

Coding

jgraph

drawiodiagramsdiagram-generationmermaid

Tool

A2A Adapter

Connectors

hybroai

Python library that exposes agent CLIs and frameworks as Agent-to-Agent (A2A) Protocol servers

a2ajson-rpcagent-interopprotocol-adapter

Tool

Agent Flow

Monitoring

patoles

Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.

agent-visualizationobservabilitydebuggingide

Tool

Auth0 for AI Agents (Auth for GenAI)

ConnectorsDeployment

auth0

Auth SDKs for agents: token vault and exchange, CIBA async approvals and fine-grained authorization, with LangChain/LlamaIndex/Vercel AI SDK integrations.

token-vaultoauthauthhuman-in-the-loop

Tool

Google Workspace CLI

ConnectorsInterface

googleworkspace

Command-line tool for the full Google Workspace API, built dynamically from Google's Discovery Service, with agent skills

productivitycligoogle-workspaceoauthskill

Tool

VulnHunter

CodingSecurity

capitalone

Agentic AI security tool that applies proactive, attacker-first analysis directly to source code.

vulnerability-scannerstatic-analysispenetration-testing

Tool

Metronix Memory

Memory

mtrnix

Metronix Memory is a self-hosted memory backend for agents over MCP: ingest files and Saa...

ragknowledge-graphlocal-firstollama

Tool

Nanobrowser

Interface

nanobrowser

Open-source Chrome extension for multi-agent AI web automation using your own LLM API keys

pluginmulti-agentbrowser-automationplaywright

Tool

OpenLLM

Deployment

bentoml

Run any open-source LLMs (Llama 3.3, Qwen2.5, Phi3 and more) or custom models as OpenAI-compatible APIs with a single command.

llamamistralopenai-compatiblelocal-first