Catalogue

Midscene

QAInterface

web-infra-dev

Vision-driven UI automation that acts from screenshots and natural-language steps across web, mobile, and desktop

playwrightcomputer-usemobile-automationvision-language-model

NeMo Agent Toolkit

CodingMonitoringQA

NVIDIA

Library for connecting, profiling and optimizing teams of agents across frameworks.

profilingobservabilityevaluationmulti-agent

Netdata

DeploymentMonitoring

netdata

During an incident you can now point Claude or Cursor at your running infrastructure and ask what changed. Netdata ships

observabilitytelemetryanomaly-detectionmcp-server

Oh My Codex

CodingInterface

Yeachan-Heo

OmX - Oh My codeX: Your codex is not alone. Add hooks, agent teams, HUDs, and so much more.

multi-agentcodexskillplugin

OmniRoute

Inference

diegosouzapw

AI gateway fronting many model providers behind one endpoint, with token-saving compression, auto-fallback, and routing for coding CLIs

gatewaytoken-optimizationmulti-providerauto-fallback

OpenAI Agents SDK

CodingVoiceSecurity

openai

Python framework for multi-agent workflows with handoffs, guardrails, sessions, sandbox and voice agents, and built-in tracing

multi-agentguardrailsobservabilitysandbox

OpenLIT

MonitoringSecurity

openlit

Open-source AI engineering platform with OpenTelemetry-native LLM observability, evaluations, and prompt management

telemetryevaluationpromptguardrails

OpenSandbox

DeploymentCoding

opensandbox-group

If you're adopting coding agents at work, OpenSandbox gives you the runtime layer: one API, `osb` CLI, MCP server, Docke

sandboxcode-interpreterkubernetesdocker

Platform

OpenShell

SecurityDeployment

NVIDIA

Sandboxed runtime for autonomous agents, with declarative YAML policies enforced at the HTTP method and path level

sandboxnetwork-policydockermicrovm

Opik

Monitoring

comet-ml

Open-source platform for tracing, evaluating, and monitoring LLM and agentic applications

observabilityevaluationpromptlangchain

Platform

Qdrant

CodingMemory

qdrant

Open-source vector database and similarity-search engine with filtering, hybrid search and a managed cloud.

vector-dbhnswhybrid-searchsemantic-search

Strands Agents

Coding

strands-agents

Model-driven Python SDK for building agents with tools in a few lines.

sdkmulti-agenttool-callingcloud

Supervision

DeploymentCodingMonitoring

roboflow

Reusable computer-vision utilities for detection, tracking and annotation pipelines.

videocomputer-visionobject-detectionobject-trackingannotation

The verification layer for the agentic coding era. AI ships code in minutes — verifying it hasn't. testsprite opens your live app, uses it like a real user, and shows your coding agent exactly what broke.

playwrightbrowser-automationclicoding-agent

Activepieces

Connectors

activepieces

Open-source Zapier alternative with a TypeScript pieces framework whose integrations double as MCP servers for LLMs

productivityorchestrationagent-buildermcp-server

AG2

Coding

ag2ai

Open-source framework for building AI agents and orchestrating cooperation among multiple agents

multi-agentautogenconversable-agentorchestration

Agent Development Kit (ADK)

CodingQADeployment

google

Google's open-source SDK for building, evaluating and deploying multi-agent systems.

multi-agentadk-webevaluation

Agentgateway

Deployment

agentgateway

Open source proxy built on AI-native protocols (MCP & A2A) that provides drop-in security, observability, and governance for agent-to-LLM, agent-to-tool, and agent-to-agent communication across any framework and environment.

gatewaya2aproxyobservability

AI Memory

Memory

akitaonrails

Cross-agent, cross-machine memeory. Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendors

cross-agentlong-term-memoryhandoffmulti-user

Axolotl

Training

axolotl-ai-cloud

Open-source framework for fine-tuning and post-training large language models across many architectures and hardware setups

fine-tuneloramoequantization

Beads

CodingMemory

gastownhall

Beads provides a persistent, structured memory for coding agents. It replaces messy markdown plans with a dependency-aware graph, allowing agents to handle long-horizon tasks without losing context.

issue-trackercoding-agentdependency-graphdolt