Your pair programmer, on rails.
Lucid Train reads your repo, writes reviewable diffs, runs commands, draws the architecture and watches the dashboards — in one native desktop app, or one 6 MB Rust binary in your terminal. Your models, your machine.
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 — open 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, bring your own key, or sign in for hosted frontier models — no API keys to manage.
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
One login
Sign in with Google — hosted frontier models, one monthly bill, no API keys.
GLM 5.2
Kimi K2.7 Code
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. One monthly bill, no API keys.
Local is free. Cloud scales with you.
Run local models at no cost. For hosted frontier models, pick a cloud plan — no API keys to manage.
Payments processed securely by Dodo Payments. Cancel anytime — access lasts through the paid period. Upgrades are prorated immediately.
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 — 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 — open harnesses on open models. Lucid Train is built for exactly this.
Get the desktop app, or the binary.
One native app for macOS — or one 6 MB Rust binary for your terminal.