Catalogue

Harness

Maka

Coding

apache

Apache Maka (Incubating) is a local-first AI agent workspace. Model messages, tool calls, tool results, permission decisions, and terminatio

local-firstdesktopsandboxevent-sourcing

Platform

Omnigent

CodingSecurity

omnigent-ai

Open-source meta-harness that orchestrates Claude Code, Codex, Cursor, and custom agents behind one interface with policies and sandboxing

codexmulti-agentgovernancesandbox

Platform

Pomerium

Security

pomerium

Open-source identity-aware reverse proxy that puts policy-based authn/authz in front of apps, agents and MCP servers.

zero-trustproxyidentity-awaregovernance

Tool

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

Tool

iFixAi

MonitoringSecurity

ifixai-ai

Catch your AI's mistakes and blind spots before your customers or regulators do..

governancered-teamevaluationcli

Tool

LoopX

CodingMonitoring

huangruiteng

Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding a

control-planelong-horizonmulti-agentgovernance

Tool

Agent Governance Toolkit

SecurityMonitoring

microsoft

Policy enforcement, zero-trust identity, execution sandboxing, and audit logging for autonomous AI agents across frameworks and languages

zero-trustsandboxgovernanceowasp

Tool

AgentTeams

CodingMonitoring

agentscope-ai

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

matrixmulti-agenthuman-in-the-loopgovernance

Tool

Entire CLI

CodingMonitoring

entireio

📜 Entire CLI hooks into your Git workflow to capture AI agent sessions as you work. Sessions are indexed alongside commits, creating a sear

session-managementcheckpointsgitgovernance

Tool

ac.tandem/docs-mcp

SecurityMemory

frumu-ai

governancehuman-in-the-loopgoverned-execution

Tool

MIND-Mem

Memory

star-ga

GitNexus turns a repo into an AST‑driven knowledge graph directly in the browser: Tree‑sitter parses the code, KuzuDB st

hybrid-searchbm25vector-dblocal-first

Harness

SandBase Harness

SecurityMonitoring

sandbaseai

Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a n

sandboxlocal-firstgovernancesession-replay

Tool

Forge

DeploymentSecurity

initializ

Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environmen

skilla2akubernetesegress-control

Tool

Imcodes

MemoryCodingInterface

im4codes

Messaging, memory, and review layer around terminal coding agents with shared context, supervised execution, and cross-provider audit

multi-agentremote-controlshared-memorycodex

Tool

Gini Agent

MemoryInterfaceMonitoring

Open-Curiosity

The agent that remembers and learns.

productivityassistantlocal-firstskillhuman-in-the-loop

Tool

Spacedock

CodingQA

clkao

Pi ships four tools ... read, write, edit, bash ... and calls it done. No MCP, no sub-agents, no permission dialogs, no

human-in-the-loopmulti-agentorchestrationgovernance

Tool

Collective Intelligence

Inference

ailinone

Point an AI agent at your company database and it writes SQL that looks right and gives the wrong answer, because it doe

gatewaymulti-providerconsensusopenai-compatible

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

EnterpriseAgentFramework

CodingSecurityConnectors

w8123

面向 OA、ERP、CRM、工单等企业系统快速构建智能体，让 AI 在权限、审计与治理约束下安全调用真实业务能力。Build agents quickly for enterprise systems such as OA, ERP, CRM, and ticketing, en

a2atool-callingraggovernance

Tool

App Store Preflight Skills

Coding

truongduy2611

AI agent skill that scans iOS and macOS projects against Apple's guidelines to flag likely App Store rejection issues before submission

iosmacosapp-storeskill

Tool

Hermes Labyrinth

Monitoring

stainlu

Read-only Hermes dashboard plugin mapping agent journeys as ordered crossings with redacted exports

observabilitydashboard-pluginredactiongovernance

Agentforce

CodingDeployment

Salesforce's platform for building, deploying and governing agents over CRM data, with Agent Builder and Data Cloud grounding.

salesproductivitysalesforcegovernanceagent-builder