Agent System · Python

Domicile

Home for persisent semi-autonomous agents/companions

jerry howell@openconstruct · Atlas 64.1 · #14= builder

View on GitHub Open jerry howell's Atlas

What it is

Domicile is a continuous agent system with a persistent memory and tool usage capabilities, designed to run locally. It includes a training component using GRPO to improve the agent's performance on custom-generated scenarios.

Scored at74e39927 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

AI Agents90%
NLP & LLMs70%
Machine Learning60%
MLOps20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the AI Agents board

Whole board

RankProjectBuilderFieldMerit

19forgeLibrary / Framework · RustForgeKit is a Rust SDK for code intelligence and agent workflows, offering graph-based code analysis, deterministic and ReAct agent loops, and a DAG-based workflow engine.63.9/100AdvancedLuiz Cesar SpiesAI Agents
20motionvault-agent-kitAI Developer Tool · JavaScriptThe MotionVault Agent Kit is an MCP server that provides 40 tools for AI agents to build cinematic websites, including template discovery, motion planning, design systems, code generation, and source delivery. It is designed to be used by AI agent clients like Claude Code via…62.2/100AdvancedMaster MindAI Agents
21DomicileAgent System · Python61.0/100Advancedjerry howellAI Agents
22MiroFish-LocalAgent System · PythonMiroFish-Local is a fully local multi-agent simulation engine that generates AI agents to model public opinion and social dynamics from input documents, using a knowledge graph (Neo4j) and local LLMs (Ollama/Gemini) for agent behavior.60.5/100AdvancedYudhis PratamaAI Agents
23VoyaAgent System · DartVoya is a full-stack travel planning application featuring a Flutter mobile app and Django backend, with a multi-agent AI assistant that integrates flight search, document scanning, and hotel maps while minimizing LLM calls through pre-validation and contextual grounding.59.8/100AdvancedAnduAI Agents

What it is

Where it counts

Around it on the AI Agents board

More from jerry howell