Try for free

Ultron Docs

Welcome to
Ultron Documentation

Resources
Skills

Try a skill

Competitive analysisNewPull rivals, score positioning, surface gaps.VC prospectorBuild a target list of investors with thesis fit.Cold outreachMulti-step sequences with intent aware copy.Content pulseDaily content engine across long form and social.Contract draftGenerate, review, and negotiate from a clause library.Morning briefingWhat changed overnight in your pipeline and inbox.
How it ships

From command to production.

Recent commits· main
05-12Ultron joins your calls - Recall.ai bot drops in, takes structured notes, and writes a striker-post-call deliverable to your CRMcalls
05-12Computer is stable - persistent E2B sandbox per workspace with a VNC pipeline so the agent can drive a real browser end-to-endcomputer
05-12Background jobs center - donut indicator under the chatbox plus a full panel that tails every running and recent jobjobs
05-08502 → sandbox_dead, start.sh boot resilience, booting state, safer reconcilersandbox
05-08add quote + stat_card primitives + 2 new layout templatescarousel

What shipped, when.

Every entry is a real production deploy. Subjects come straight from the commits, no rewrites.

View full changelog
Active plan· 3 steps
pull rivals + score positioning2.1s
draft outreach sequencerunning
sync to CRM + notify HITLqueued

Plan, run, observe, iterate.

Ask in plain English. Ultron drafts a plan, runs the skills, and pauses at every decision that leaves the building.

Workflow runtime
> /cold
/competitive-analysisresearch
/cold-outreachsales
/morning-briefingops
/vc-prospectorlead-gen

Run a skill.

Trigger any of the 57 skills from chat with a slash command or plain language.

View slash commands
quarterly-recap· research
skill.yaml192 B
prompt.md1.4 KB
tools.allow86 B
registry reload pending

Build a skill.

Scaffold a skill with a manifest, a tool allow list, and a model tier. Loaded on next start.

Skill anatomy
Explore

Skills, techniques, and field notes.

The catalog lives in the docs. Hand crafted workflows live in Techniques. Field tested teardowns live in Resources.

Skill catalogEvery skill by category, with its manifest, tools, and model tier.TechniquesReusable, hand-crafted workflows you can run end to end.ResourcesField-tested teardowns, straight from real campaigns.ArchitectureHow chat, skills, memory, sandbox, canvas, and swarm fit together.
Models

Every frontier model, one runtime.

One interface across Anthropic, OpenAI, DeepSeek, Moonshot, xAI, MiniMax, and Qwen. Pin a model per skill, or let the router choose.

claude-opus-4-8
claude-sonnet-4-6
gpt-5.5
DeepSeek-V4-Pro
model-router
Kimi-K2.6
grok-4-20-reasoning
FW-MiniMax-M2.5Fireworks
qwen-qwen3.5Hugging Face
Leaderboard

How they stack up.

Scored on quality, safety, throughput, and cost. Higher quality and throughput win; lower violation rate and cost win.

ModelQuality index
  • 01gpt-5.50.82
  • 02claude-opus-4-60.82
  • 03gpt-5.40.81
  • 04claude-opus-4-50.81
  • 05Kimi-K2.60.79
  • 06DeepSeek-V4-Pro0.78

Indicative benchmark figures. Accent marks the best result in each column.

Systems

Six systems that make it run.

  • Skills57 skills across 8 categories. Composable, registry based, scoped tools and model tier per skill.
  • MemoryThree storage surfaces, hybrid retrieval, and a four step conversation compression cascade.
  • WorkspacePersistent sandboxes with a live remote desktop, bundled engineering skills, and a 60 second reconciler.
  • CanvasRuntime renderer with 30+ block types. Export to PNG, PDF, or save to Brain.
  • Tools91 native tools plus external servers. Provider modules with status labels and HITL approvals.
  • Background jobsReconcilers, janitors, lifecycle emails. The quiet machinery that keeps state honest.