devops-infra MCP Server
Multi-tool AI agent harness — 22 skills, self-evolving engine, unified memory, autonomous spec-to-PR pipeline. Works with Claude Code, Codex, Cursor, OpenCode, and Cline.
Discovered via agent-topic:ai-agent and last synced 3mo ago.
Install instructions not detected yet
Check the source repository for the latest setup steps.
How it works
Same error N+ times
`evo-go-care`
`stream`
Manual / MCP
Edit success → build/test fails
`evo-py-care`
With
When
domain-specialist, integration-tester
Auto (reflect)
RETRY{"retry < 3?"} RETRY -->
Active hooks
Purpose
Auto (reflect)
PAUSE["Pause\nuser decides"]:::human PAUSE -->
0.87
guard, observe, resume
What it does
Auto (reflect)
Stuck on same file
`evo-rs-care`
`enabling`
Manual / MCP
0.65
Detects
Presets
Created by
Manual / MCP
When
all hooks + future strict-only checks
Auto (reflect)
`platform`
Manual / MCP
Why not enhanced
Edit↔Error alternating
Add node with auto-importance by type (or explicit 0.0–1.0)
ABORT(["Abort"]) SHIP --> EVOLVE["Evolve\nauto-analyze session"]:::auto EVOLVE --> DONE(["Orbit Complete\nconsolidated report"]):::auto classDef human fill:#4a4a6a,stroke:#9b9bcc,color:#fff classDef auto fill:#1a5c3a,stroke:#4caf7d,color:#fff ``` **Purple** — human steps: mode selection (unclear → interactive), 3× check failure pause. **Green** — clear + complex → council auto-spec; clear + simple → direct build; both fully autonomous. State persisted in `$HARNESS_DIR/orbit/PIPELINE-{timestamp}.json` — survives context compaction. > **Caveats**: The agent may bypass the pipeline when modifying orbit itself or editing docs only. See [Known Issues (Agent Judgment)](#known-issues-agent-judgment). --- ## Auto Skills (Ring 2) Skills trigger automatically based on context. You don't invoke them.
Project-scoped smart recall (no hint)
Agents
Graph traversal from a node ID (finds connected knowledge)
Keyword search (full-text), ranked by importance
Smart contextual recall with hint + project + graph neighbors
Filter by tag/type/project