MCP servers and skills: search, filter by where they run, and compare.
Chaos engineering for MCP agents: a stdio proxy that injects timeouts, errors, malformed JSON, schema drift and stale results, plus a benchmark that measures how agents recover.
PythonMITFew starsNo key
Fault injection toolkit for agent systems. Inject latency spikes, partial failures, 429s, malformed tool outputs, and stale context between agents and their tools. Scenario-driven. Prove your circuit
SkillMIT★ 2Few starsNo key
Chaos engineering for AI agents — a fault-injecting MCP proxy. Zero code: point your agent's MCP config at the proxy and break things on purpose, before production does.
PythonApache-2.0Few starsNo key
Multi-tenant chaos-engineering / API-resilience control plane, demonstrating fault injection, optimistic concurrency, Kafka-driven execution, and distributed-systems resilience. Java 21, Spring Boot 4
SkillMITFew starsNo key
Property-based reliability testing for tool-using AI agents under partial failures.
PythonApache-2.0★ 1Few starsNo key
Chaos testing for AI agents. Break the MCP tools your agent depends on, score how it copes, fix what broke. Claude Code plugin + GitHub Action.
GoMITFew starsNo key
Fault injection and reliability scoring for MCP servers
PythonApache-2.0★ 1Few starsNo key
ClaudeOps hAIveMind - Distributed AI collective memory MCP server for DevOps automation and multi-agent coordination
PythonMIT★ 7No key
A local test harness for AI agent systems. Compare the same work before and after a change.
SkillApache-2.0Few starsNo key
A lab for a per-call policy gate, an action monitor and a scripted approval step over an incident agent. Closed at a baseline, 2026-09-06.
SkillMITFew starsNo key
Built an autonomous SRE agent using Gemini 3 API + MCP (Model Context Protocol) that operates a live Kubernetes cluster through 20+ tool integrations — injecting real failures, detecting incidents fro
SkillMIT★ 1Few starsNo key
A benchmark and evaluation platform for AI-driven Kubernetes incident response, with reproducible fault injection, evidence-based grading, and reference agents for diagnosis, remediation, and learning
MCPLink onlyFew stars
Hosted streamable HTTP MCP server for Cloud World Model: simulate cloud infrastructure and estimate cost, latency and resilience before deploying or changing infrastructure. Multi-cloud world model fo
MCPLink onlyFew stars
Open-source AI Operations platform for multi-agent systems featuring OpenTelemetry instrumentation, SigNoz observability, MCP-powered diagnostics, chaos engineering, workflow replay, and AI cost intel
MCPLink only★ 2Few stars
From-scratch, event-driven, resident Agent Team harness with durable recovery and inspectable context.
PythonApache-2.0Few starsNo key
Chaos on your disk, order in your AI's context. Local memory for Claude Code and Codex: indexes notes, chats and code in the background, attaches only what matters to each prompt and marks what was la
PythonAGPL-3.0★ 3Few starsNo key
Who stands behind it
