Brain
Provides an adapter for Cloudflare as an AI provider route, enabling Ultron to call Cloudflare-hosted models.
Routes jobs to Google model APIs as a direct provider tier.
Routes jobs to Hugging Face model APIs as a direct provider tier.
Routes jobs to NVIDIA NIM model APIs as a direct provider tier.
Routes jobs to Ollama Cloud as a direct provider tier and can use local OpenAI-compatible model servers.
Routes jobs to OpenAI model APIs as a direct provider tier.
Routes jobs to Perplexity model APIs as a direct provider tier.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Ultron
One command line and one MCP server in front of every AI you can reach: cloud model APIs, subscription CLIs, local models and coding-agent harnesses. You hand Ultron a job; it picks the best available model or agent for that kind of job, falls through when one is down or out of quota, checks the result, and learns from the outcome.
Ultron grew out of AI Fleet (a task-card dispatcher) and two brain-structured rewrites of it
(ai-neural-network and neural-fleet, merged 2026-11-14). The Python package is still named
ai_neural_network; the commands are ultron and brain (same program).
Quick start
git clone https://github.com/d123d/ultron.git
cd ultron && uv venv && uv pip install -e ".[dev]"
uv run ultron slots # what you can reach: providers, models, harnesses
uv run ultron jobs # kinds of work and the models each one uses
uv run ultron job quick "Say hello"Keys are read from ~/.secrets/.env (or the environment) by the names in
src/ai_neural_network/workers.yaml. No key belongs in this repo: CI runs gitleaks over the
full history on every push, and run logs are redacted. A provider with no key simply stays
unavailable and its fallbacks answer.
Related MCP server: DZ23 Subagents Universal MCP
The three ideas
Provider slots. One slot per provider: endpoint or CLI login, concurrency, key state, and
every model it serves (ultron slots --refresh pulls the live /models lists). Any listed model
can be called without configuring it: ultron ask "..." --tier "nvidia:<model id>,".
Local harnesses (Codex, OpenCode, Pi, Antigravity, Copilot, Claude Code, Muse, OpenHuman) have
slots too.
Job slots. config/jobs.yaml maps a kind of work to an ordered list of models or to an agent
harness. ultron job <kind> "<prompt>":
Kind | What runs |
| fast free text models |
| strongest free reasoning and long-context models |
| three providers answer, majority wins |
| image QC ( |
| local model only; nothing leaves the machine |
| subscription models |
| an agent harness works in |
| handed to OpenHuman's card queue |
Board and daemon. ultron board add --text "<goal>" --cwd <repo> --done-when "<check>" queues
agent work; --dep chains cards so they run one at a time; --hold parks one. ultron daemon
(a logon task on Windows) takes one ready card a minute, runs it on the first free harness, fails
over to the next harness on quota or crash, verifies with the card's checks and closes or reopens
it. Cards left in progress by a dead daemon are reopened on restart.
Details and the list of defects found in live use: docs/SLOTS.md.
Under the hood: the network
Workers and model tiers are neurons in five regions (sensory, memory, association, prefrontal, motor) joined by weighted excitatory and inhibitory synapses. A task is a stimulus: it spreads, recruits a firing population, the population does the work, checks verify it, and the outcome rewires the weights (Hebbian learning with STDP-lite, neuromodulation by cost, learned inhibition, sleep consolidation). See docs/ARCHITECTURE.md and docs/BRAIN-MAP.md.
ultron status
ultron excite "fix the parser" --capability code --trace # who would fire
ultron fire "summarise notes" --capability text # propagate, run, verify, learn
ultron leader elect # which executive model is available
ultron doctor # health and quota of every worker and tierShipped seed weights are config/weights.json; what a machine learns is saved in its state
directory, never in the repo.
Skills and tools
Worker prompts carry the working rules (smallest complete change, terse output, never fake a
check) and, per task topic, the paths of matching skills from the machine's skill library plus its
tool registry: 3D worlds and assets, animation, cinema, fiction, audio, images, documents, code.
Topics are in config/skills.yaml; install skills with skills.sh. A few
skills ship in skills/. See docs/SKILLS.md.
Providers
Direct tiers for OpenRouter, NVIDIA NIM, Ollama Cloud, Google, OpenAI, Anthropic, Mistral, Cohere,
Groq, Cerebras, Together, Fireworks, DeepInfra, SambaNova, DeepSeek, xAI, Perplexity, Moonshot,
MiniMax, Hugging Face, OpenCode Go; adapters for Azure, Bedrock, Vertex and Cloudflare;
subscription routes through the claude, codex, agy, copilot and muse CLIs; local models
through any OpenAI-compatible server. Matrix: docs/PROVIDERS.md; vendor
quirks: docs/PROVIDER-BEST-PRACTICES.md.
For other agents
ACCESS.md: clone, MCP config and the worker contract. MCP tools include brain_job,
brain_slots, brain_ask, brain_run, brain_fire, brain_doctor, brain_leader.
Honest limits
Built and tested on one Windows 11 workstation; CI runs the tests on Linux. Paths in
workers.yaml,config/skills.yamland the board settings point at that machine: edit them.Job-slot model order is hand-set from live measurements, not learned yet.
Health state is safe across threads, not across processes.
MIT licence.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
The OpenRouter for tools. One MCP connection gives any AI agent 254 hosted tools, pay per call.
Related MCP Servers
- AlicenseBqualityFmaintenanceEnables AI assistants to intelligently select and switch between different AI models (OpenAI, Anthropic, etc.) within the same conversation based on task requirements. Provides a unified interface for accessing multiple AI providers through a single MCP tool.1107 npmMIT
- AlicenseAqualityBmaintenanceEnables users to delegate text and code tasks across multiple AI models with automatic failover, maintain shared mission memory and checkpoints across MCP harnesses, and coordinate parallel role-based subagents. It also supports model discovery, provider inventory, health checks, and stdio/HTTP tool access while leaving patches and tests to the harness.24MIT
- AlicenseNot gradedqualityCmaintenanceLets MCP clients route prompts and tasks to user-selected AI providers and models for coding, reasoning, planning, agentic analysis, image generation, and deep research, with configurable fallback order.13 npmMIT
- AlicenseAqualityBmaintenanceEnables any AI agent to connect to any OpenAI-compatible LLM provider through a unified MCP interface, with automatic failover, caching, cost tracking, and multi-model consensus.13MIT