Hephaestus

data-ai MCP Server

Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, memory and security gates.

Verified
data-aidata-ai
5 views74 stars13 forksApache-2.0

Why This Matters

Discovered via agent-topic:autogen and last synced 3mo ago.

Verified
Source
agent-topic:autogen
Stars
74
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
15
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (15)

Path

Best for

Hermes

Persona and memory-centered local agent runtime

Task

Open this

Browser

`https://agentlas.cloud/desktop` or the OS download command

10-single-agent-builder

One installable worker with skills, memory contracts, runtime adapters, and verification

30-agentlas-packager

A cleaned Agentlas package for Desktop import, terminal use, Codex, Claude, Gemini, or public GitHub release

Format

Status

OpenClaw

Local identity and workspace agent loop

Goal

Start here

Scorecard

Native Codex

Runtime

Check

Codex

`codex mcp list` in the terminal; private agent features should open browser sign-in on first use

Antigravity

Open your workspace

20-multi-agent-team-builder

A multi-role operating team with HQ, PM Soul, Memory Curator, Policy Gate, eval, QA, and handoffs

unsupported_pending_adapter

The storage default is SQLite at `.agentlas/ontology-runtime.sqlite`, ignored by Git. The schema includes `sources`, `source_lineage`, `chunks`, `chunk_fts`, `entities`, `entity_aliases`, `relations`, `memory_candidates`, `memory_candidate_events`, `working_memory`, `runtime_adapters`, and `schema_migrations`. Basic local run: ```bash bin/ontology ingest examples/ontology-corpus --scope internal bin/ontology query "Project Helios Memory Curator" --agent verifier bin/ontology graph entity "Project Helios" bin/ontology memory candidates bin/ontology working-memory read --agent verifier bin/ontology verify ``` The query response includes relevant chunks, related entities, relation edges, evidence refs, source spans, confidence, Memory Curator candidate suggestions, and optional Agent Working Memory writes. It is not a vector-only result. The runtime stack is layered: