Code-enforced incident-response agent that investigates SigNoz alerts, publishes evidence-backed root-cause claims, and gates every action behind a safety policy. Built for Agents of SigNoz hackathon.
Every claim backed by evidence. Every action gated by code. Nothing is trust the model. Everything is prove it in telemetry.
Agent K is a code enforced incident response agent for a FastAPI RAG support answering service. When a SigNoz alert fires, Agent K investigates the failure through the SigNoz MCP server, publishes only evidence backed root cause claims, executes a sandboxed rollback only when a code based policy allows it, and records its own cost and behavior as telemetry so every decision is auditable in SigNoz.
Built for the Agents of SigNoz hackathon (WeMakeDevs x SigNoz), Track 01: AI and Agent Observability (July 20 to 26, 2026).
AI applications can fail in unusual ways: slow, expensive, inaccurate, or stuck in retry loops, without producing a normal server error. An engineer usually has to comb through traces, metrics, logs, and deployment history to understand what happened, and an AI agent that investigates can itself make unsupported guesses or take unsafe actions.
Agent K makes every investigation traceable, every conclusion verifiable, and every action controlled by code.
Problem without Agent K What Agent K does about it --- --- Agent makes a root cause guess with no proof Law 1 strips any claim that has no resolvable SigNoz evidence link Agent recommends an action the model thinks is fine Law 2 runs a code based policy gate before any action executes Agent runs silently, cost spirals, loops forever Law 3 records every call, token, query, and verdict as a span
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/SujalXplores--Agent-K.html)
Self-hosted documentation RAG pipeline that serves semantic search to LLM agents over the Model Context Protocol.
ashuio/livewallA live status board your AI agent writes while it works. Send a JSON board spec over MCP, HTTP or the CLI; a browser renders it live over SSE.
MuhittinYilmazer/akanaSelf-hosted, local-first AI assistant server: swappable LLM providers, review-gated memory, an encrypted vault, and wake-word voice. No accounts, no telemetry.
java-ai-in-action/framework-compareSpring AI vs LangChain4j vs SAA 三框架同台对比（配套篇2）
bybit-exchange/kaasTurn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.
zja0011/edgesentinel-visionopsJetson Nano edge AI vision Agent Harness: real-time video analytics, MCP tools, event evidence, DeepSeek online/offline, secure recovery
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.