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.

Download for macOSApple Silicon & Intel · .dmg
$curl -fsSL https://lucidtrain.com/install.sh | sh
prefer the CLI? →
LOCAL MODELS FREE · OR RUN IN THE CLOUD · YOUR MACHINE, YOUR KEYS
CODEAUDITDIAGRAM
📁 lucid-train
Sessions
fix auth flow
3 tools · now
add rate limits
12m ago
refactor store
1h ago
~/code/lucid-train
kimi-k2.5 ▾
The login test is flaky — fix it and re-run.
● generating…
0% allowanceAArnab
Rust TUI· Tauri desktop· 15+ models· local & cloud· MCP & skills
The desktop app

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.

↗ Open in ▾📁 lucid-train
workspacetalindrew×vion×+
Chats
new session
agent · lucid-train
21/7/2026, 1:26 PM
agent · lucid-train
19/7/2026, 3:56 AM
agent · lucid-train
16/7/2026, 12:26 AM
Commands ▸
Type / in the message box to search commands.
CODEpersonal_project/lucid-train
agent ▾⊙ morestart
The login test is flaky — find the race and fix it.
Enter sends. Shift+Enter adds a line. ↑↓ history. Use /model, /plan…
0% allowanceAArnab Bhattacharya ▲
↑ click the tabs — Code · Audit · Dashboards · Connectors · Diagram
Agent orchestration

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.

Per-role model routing. Assign a different model to Plan, Edit and Vision — cheap where it can be, frontier where it counts.
Concurrent projects. Every open workspace runs its own agent sidecar — several repos working at once, ⌘K to jump.
Plan → approve → apply. Propose-only until you say go; then the same agent flips to auto and applies its plan.
“Audit my dependencies, then draw the architecture.”
LUCID ORCHESTRATOR
↓   ↓   ↓   ↓
Plan role
qwen3:4b · fast
Edit role
kimi-k2.5 ● running
Vision role
gpt-oss · reads diagrams
Persona
dep-audit ● running
3 projects3 sidecars · concurrentMCP tools attached
Built for real work

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.

⌘K

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.

>_ The CLI

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.

$curl -fsSL https://lucidtrain.com/install.sh | sh
/agent full tools
/plan propose-only
/research cited, no shell
~/code/lucid-train — lucid-train
$ lucid-train
╭────────────────────────────────╮
>_ Lucid Train (v0.2.0) │
│ model: kimi-k2.5
│ provider: openrouter
│ directory: ~/code/lucid-train
╰────────────────────────────────╯
map repo · done
locate flaky test · done
thinking… the refresh isn't awaited
• Edited src/auth.rs
cargo test · 24 passed 1.8s
tokens: 12.4k in · 3.1k out
Models · open models first

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.

Local · free

Ollama, zero-setup

/download installs Ollama and pulls the best model for your RAM. 100% offline.

gpt-oss:20b
qwen3-coder:30b
deepseek-r1
OpenRouter · BYO key

15+ models

Bring your key — stored locally, sent only to the provider.

GPT · Gemini · Grok
DeepSeek V4 · Qwen
GLM · MiniMax
Cloud · no keys

One login

Sign in with Google — hosted frontier models, one monthly bill, no API keys.

DeepSeek V4 Pro
GLM 5.2
Kimi K2.7 Code
Benchmarks

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.

$lucid-train models --bench
DeepSeek V4 Pro
Lucid's default · cheapest near-frontier
LiveCodeBench
93.5%
#1 of any model
SWE-bench Verified
80.6%
GPQA Diamond
90.1%
reasoning
GPQA Diamond · graduate-level science90.1%
MMLU-Pro · expert knowledge87.5%
coding · agentic
LiveCodeBench · competitive programming93.5%
SWE-bench Verified · real bug fixes80.6%
Terminal-Bench 2.0 · agentic terminal use59.1%
SWE-bench Pro · hard real-world SWE55.4%

The value pick: tops LiveCodeBench, 1M-token context for whole-repo work, and output runs ~30× cheaper than GPT-5.5.

context 1Min $0.43/1Mout $0.87/1Msource: Artificial Analysis, OpenRouter & vendor reports — Jun 2026

Source: Artificial Analysis, OpenRouter & vendor reports — Jun 2026

Price vs the frontier

Near-frontier coding, 7×–34× cheaper.

The same everyday coding work, side by side — sorted by what you actually pay per million output tokens.

ModelSignal$ / 1M output
included in a plan your own API key
DeepSeek V4 ProCLOUD
Cloud · DeepSeek
80.6%
SWE-bench Verified
$0.87
GLM 5.2CLOUD
Cloud · Z.ai
68.8
AA Coding Index
$3.00
Kimi K2.7 CodeCLOUD
Cloud · Moonshot
> GPT-5.4
SWE-bench Pro
$3.50
Kimi K3CLOUD
Cloud · Moonshot · open-weight
agentic
repos · tools · 1M ctx
$15.0
Claude Opus 4.8
Anthropic · API key
88.6%
SWE-bench Verified
$25.0
GPT-5.5
OpenAI · API key
frontier
coding / reasoning
$30.0

Sources: Artificial Analysis, OpenRouter & vendor reports — Jun 2026. One monthly bill, no API keys.

Cloud plans

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.

or in your terminal: lucid-train login

Payments processed securely by Dodo Payments. Cancel anytime — access lasts through the paid period. Upgrades are prorated immediately.

In the news

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.

Artificial Analysis@ArtificialAnlys
benchmarks
DeepSeek is back — V4 Pro tops the open-weight charts

The independent benchmark lab's read on the open-weight frontier: DeepSeek V4 Pro and Flash reset the price/intelligence curve.

read →
Anthropic
frontier
Introducing Claude Opus 4.8 — 88.6% on SWE-bench Verified

The closed frontier at $25/1M output. Lucid's open models land within striking distance for everyday coding — at a fraction of the price.

read →
Moonshot AI
agentic
Kimi K2.7 Code — open agentic intelligence

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.

read →
Latent Space@swyx
dev tools
The terminal agent is eating the IDE

swyx & the AI engineering crowd on why coding moved back to the terminal — exactly the surface Lucid Train is built for.

read →
OpenRouter
rankings
GLM 5.2 — highest open-weight Artificial Analysis intelligence

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.

read →
Artificial Analysis@ArtificialAnlys
benchmarks
DeepSeek is back — V4 Pro tops the open-weight charts

The independent benchmark lab's read on the open-weight frontier: DeepSeek V4 Pro and Flash reset the price/intelligence curve.

read →
Anthropic
frontier
Introducing Claude Opus 4.8 — 88.6% on SWE-bench Verified

The closed frontier at $25/1M output. Lucid's open models land within striking distance for everyday coding — at a fraction of the price.

read →
Moonshot AI
agentic
Kimi K2.7 Code — open agentic intelligence

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.

read →
Latent Space@swyx
dev tools
The terminal agent is eating the IDE

swyx & the AI engineering crowd on why coding moved back to the terminal — exactly the surface Lucid Train is built for.

read →
OpenRouter
rankings
GLM 5.2 — highest open-weight Artificial Analysis intelligence

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.

read →
CoreWeave
inference
Kimi K2 is the best open-source model — and the fastest to serve

Why open-weight coding models are now production-grade: frontier quality, served fast and cheap at scale.

read →
codersera
showdown
Kimi K2.7 vs DeepSeek V4 — the open coding showdown (2026)

How the top open coding models stack up — the same ones Lucid Train routes to.

read →
codingfleet
head-to-head
GLM 5.2 vs DeepSeek V4 Pro — SWE-bench leader vs the algorithm king

GLM 5.2 takes the open-weight SWE-bench crown; DeepSeek V4 Pro leads LiveCodeBench. Lucid serves both.

read →
Hacker News
show hn
Open coding agents are topping Terminal-Bench

Terminal-native agents are having a moment — open harnesses on open models. Lucid Train is built for exactly this.

read →
CoreWeave
inference
Kimi K2 is the best open-source model — and the fastest to serve

Why open-weight coding models are now production-grade: frontier quality, served fast and cheap at scale.

read →
codersera
showdown
Kimi K2.7 vs DeepSeek V4 — the open coding showdown (2026)

How the top open coding models stack up — the same ones Lucid Train routes to.

read →
codingfleet
head-to-head
GLM 5.2 vs DeepSeek V4 Pro — SWE-bench leader vs the algorithm king

GLM 5.2 takes the open-weight SWE-bench crown; DeepSeek V4 Pro leads LiveCodeBench. Lucid serves both.

read →
Hacker News
show hn
Open coding agents are topping Terminal-Bench

Terminal-native agents are having a moment — open harnesses on open models. Lucid Train is built for exactly this.

read →
Install

Get the desktop app, or the binary.

One native app for macOS — or one 6 MB Rust binary for your terminal.

Download for macOS
v0.1.2 · .dmg · Apple Silicon & Intel
Signed & notarized by Apple · opens without a Gatekeeper warning
sha256 fa1cda730ec933dd534915f5807584c212321551079d2905a65eb0132c1027a3
CLI$curl -fsSL https://lucidtrain.com/install.sh | sh
FAQ

Questions, answered.

How much does it cost?

Local models are free — run them on your own machine at no cost. For hosted frontier models, choose a cloud plan ($10 / $30 / $70 per month) with a monthly token allowance and no API keys to manage.

Desktop app or CLI — what's the difference?

Same agent core. The desktop app adds Code, Diagram, Audit, Dashboards and Connectors in one window with a command palette and themes; the CLI is a single Rust binary with a keyboard-first TUI for the terminal. Use either, or both.

Can it run fully offline?

Yes — 100% offline with local Ollama models. Your code never leaves the machine, and there's no API key or telemetry. Credentials live in the OS keychain.

What is agent orchestration?

Lucid routes each turn through an orchestrator that can assign different models to different roles (plan, edit, vision) and seed each tab with a task persona. Multiple projects run their own agent sidecars concurrently.

Which models does it support?

Any OpenAI-compatible endpoint: local Ollama, OpenRouter (GPT, Gemini, Grok, DeepSeek, Qwen, GLM, Kimi…), or hosted cloud models. Context windows are tracked and the conversation compacts before overflow.