Design the system.
Then let it build itself.
Point Lucid Train at your repo and it draws the architecture, one act at a time. Then hand that diagram to the coding agent as a specification and review the diffs that come back. It runs as a native desktop app, or as one 6 MB Rust binary in your terminal.
Diagram
Four real diagrams of the opensre repository, drawn by the agent and exported straight out of the app. Pick one from the rail, drag to pan, scroll to zoom.
The diagram is the specification.
Ask for a diagram and the agent surveys the repo, then narrates the system one act at a time. Each act is a real architecture drawing with a narrator beside it. You never place a box: the agent emits components and the edges between them, and the app runs an ELK layout to position and route everything, so a diagram cannot come out overlapping.
Context
The whole system in five to eight boxes, and the edges between them.
Containers
Every service, banded by tier: client, application, data.
Data flow
One request end to end. The path stays lit and everything else dims.
Data
The stores, and what actually gets written where.
Failure
The single points of failure, marked as problems.
Implement in code →
One click turns the canvas into a markdown spec, every component, every relationship and the narrator's notes, then starts a real turn in the Code tab with it. Your DESIGN.md rides along as the authoritative specification, and a 17 KB one fits whole. The README goes with it as orientation. The agent implements against the drawing rather than against a paragraph you had to write twice.
After drawing, the app screenshots each act and hands the image back to the agent to judge, a vision pass over its own output. It fixes what is wrong and re-emits the act in place rather than piling a correction up beside the original.
Save to READMEs writes docs/<name>.svg and merges an ## Architecture section into the README beside it, idempotently, so re-running updates that section instead of stacking another copy. The design review your repo never had now lives in it.
One app. Every surface.
Chat with the coding agent, sketch architecture, audit dependencies, watch your Grafana and wire up connectors. Each tab drives the same agent core. Click through it.
One request. The right model for every job.
Lucid routes each turn through a small orchestrator. A fast model drafts the plan, a strong coder writes the diff, a vision model reads your diagrams, and task personas (dep-audit, grafana-ops, diagram) seed each tab with the right prompt and tools.
Everything you'd expect, and the parts you didn't.
Multi-project workspaces
Open several repos at once. Each gets its own agent sidecar and chat history, all running concurrently.
Reviewable diffs & approvals
Every edit lands as a green/red diff. Commands are risk-tiered: safe runs, caution & dangerous prompt, catastrophic is refused.
Command palette
Jump between tabs and projects, toggle the theme, or open the workspace in your editor, all from ⌘K.
MCP & skills
Connect any Model Context Protocol server, and install SKILL.md packs from skills.sh without leaving the chat.
Voice & vision
Push-to-talk your prompts with on-device transcription, and attach images for vision-capable models.
Light, dark & your editor
One warm editorial identity in both schemes. Detects VS Code, Cursor and Zed, then opens the workspace in one click.
Prefer the terminal?
So do we.
The same Terminal-Bench-grade harness, as a single 6 MB Rust binary with a fast, keyboard-first TUI. Live plans, thinking stream, diffs, token accounting. No IDE, no browser.
Your models. Your machine.
Any OpenAI-compatible endpoint works. Run fully local and free, or bring your own key. Your prompts go straight to the provider you pick, never through us.
Ollama, zero-setup
/download installs Ollama and pulls the best model for your RAM. 100% offline.
qwen3-coder:30b
deepseek-r1
15+ models
Bring your key. Stored locally, sent only to the provider.
DeepSeek V4 · Qwen
GLM · MiniMax
Already paying?
login claude or login codex to use the plan you already have, no API key.
ChatGPT Plus / Pro
via the official CLIs
The numbers, with their sources.
Every score below is a published third-party or vendor result, labeled with the benchmark it came from. No composite index of our own invention.
Source: Artificial Analysis, OpenRouter & vendor reports, Jun 2026
Near-frontier coding, 7×–34× cheaper.
The same everyday coding work, side by side, sorted by what you actually pay per million output tokens.
Sources: Artificial Analysis, OpenRouter & vendor reports, Jun 2026. You pay your provider directly.
The CLI is free. The desktop app is $3.
One licence for the desktop app. Everything runs on your machine, against local models or your own API keys, so there is no usage to meter and nothing to top up.
- The full agent, in one Rust binary
- Local models, or your own API keys
- Open source · no account needed
or: pip install lucid-train
- Everything in the CLI, in a native app
- Design, Diagram, Audit and Dashboards
- Local models, or your own API keys
- 7-day free trial · no card up front
Every model call goes straight from your machine to whichever provider you configure. We never see your code, and there is no usage bill to read.
Why the terminal won.
Third-party writing about the models Lucid Train runs and the shift to agentic coding. Context, not endorsements. Every link goes to its original source.
The independent benchmark lab's read on the open-weight frontier: DeepSeek V4 Pro and Flash reset the price/intelligence curve.
The closed frontier at $25/1M output. Lucid's open models land within striking distance for everyday coding, at a fraction of the price.
Coding-first, built for long tool-using runs and MCP. Moonshot reports it edging GPT-5.4 and Claude Opus 4.6 on SWE-bench Pro.
swyx & the AI engineering crowd on why coding moved back to the terminal, exactly the surface Lucid Train is built for.
Live token rankings and benchmarks for the open coding models. Lucid routes to GLM 5.2, DeepSeek V4 Pro and Kimi K2.7, no key needed.
The independent benchmark lab's read on the open-weight frontier: DeepSeek V4 Pro and Flash reset the price/intelligence curve.
The closed frontier at $25/1M output. Lucid's open models land within striking distance for everyday coding, at a fraction of the price.
Coding-first, built for long tool-using runs and MCP. Moonshot reports it edging GPT-5.4 and Claude Opus 4.6 on SWE-bench Pro.
swyx & the AI engineering crowd on why coding moved back to the terminal, exactly the surface Lucid Train is built for.
Live token rankings and benchmarks for the open coding models. Lucid routes to GLM 5.2, DeepSeek V4 Pro and Kimi K2.7, no key needed.
Why open-weight coding models are now production-grade: frontier quality, served fast and cheap at scale.
How the top open coding models stack up, the same ones Lucid Train routes to.
GLM 5.2 takes the open-weight SWE-bench crown; DeepSeek V4 Pro leads LiveCodeBench. Lucid serves both.
Terminal-native agents are having a moment, with open harnesses on open models. Lucid Train is built for exactly this.
Why open-weight coding models are now production-grade: frontier quality, served fast and cheap at scale.
How the top open coding models stack up, the same ones Lucid Train routes to.
GLM 5.2 takes the open-weight SWE-bench crown; DeepSeek V4 Pro leads LiveCodeBench. Lucid serves both.
Terminal-native agents are having a moment, with open harnesses on open models. Lucid Train is built for exactly this.
Get the desktop app, or the binary.
One native app for macOS and Windows, or one 6 MB Rust binary for your terminal.