cd /news/ai-agents/litespeed-a-local-coding-agent-with-… · home topics ai-agents article
[ARTICLE · art-132542] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Litespeed – a local coding agent with multi-model workflows

BerriAI released Litespeed, a local coding agent for the terminal and browser built around multi-model workflows, distributed as a macOS package with runtimes included so no Node or npm setup is required. Litespeed connects through LiteLLM, OpenAI-compatible APIs, native Anthropic, or ChatGPT device sign-in, and its recommended Sidekick Fusion arrangement pairs a strong driver model for planning and review with a cheaper sidekick for implementation, while the experimental LiteFusion routes 63 task categories to specific models and reasoning levels. The agent runs a local backend automatically, serves a browser UI at http://localhost:3210, and keeps saved sessions and settings outside the application package.

read4 min views2 publishedSep 17, 2026
Litespeed – a local coding agent with multi-model workflows
Image: Michielbdejong (auto-discovered)

A local coding agent for your terminal and browser, built around multi-model workflows. Use one model or combine a driver with sidekicks, workers, or experts. Follow their work, approve changes, and review the result in one conversation. Pairing models lets a faster, cheaper model handle routine work while a stronger model handles planning or difficult tasks, which can reduce cost and wait time.

Connect through LiteLLM, OpenAI-compatible APIs, native Anthropic, or ChatGPT device sign-in. Your project stays on your machine; prompts and selected context go to your chosen provider.

Download the macOS package with its runtimes included—no Node or npm setup:

curl -fsSL https://github.com/BerriAI/litespeed/releases/latest/download/install.sh | sh

Open a new terminal, then run it from the project you want to work on:

cd /path/to/your/project
litespeed

The installer sets up the litespeed command for new terminal windows (zsh or Bash). If you use the same terminal window where you installed it, run export PATH="$HOME/.local/bin:$PATH" first.

Litespeed starts its local backend automatically. Updates appear in both UIs, or run litespeed update. Saved sessions and settings stay outside the application package.

See installation, updates, and the source-build alternative. Packages support Apple silicon and Intel Macs. Git and your project's development tools remain separate.

Litespeed has its own command, separate from the LiteLLM gateway CLI. If you used an earlier version of this agent, follow the upgrade guide to carry over saved sessions and configuration.

  1. On your first launch, choose your setup, connect your LiteLLM gateway base URL andAPI key , and pick your models.Sidekick Fusion is recommended: choose a strong driver to plan and review, and a cheaper sidekick to handle implementation.LiteFusion is experimental ; its task-specific routing policy is available for evaluation. ChooseSingle model if you prefer one model for everything. Litespeed remembers the connection and models; runninglitespeed in another project opens chat directly. Gateways that do not require a key can leave it blank.
  2. Use Models or/models to change your arrangement.Ask first is the default;Allow all tools is available in permissions. The full setup is available from the web sidebar or/setup . If you already use Claude Code or Codex skills, /skills (orSettings → Project profiles ) offersImport a Claude/Codex skill… to copy one into the project — seeProject profiles and skills .
  3. Type a task. Build can edit files and run commands;Plan uses read-only tools. Type/ for command suggestions in either client; use**↑/↓** ,Tab orEnter to complete, andEsc to dismiss.Ctrl+P opens terminal commands and navigation.

See the terminal guide for shortcuts, resuming sessions, and configuration.

Once Litespeed is running, open http://localhost:3210. The browser and terminal share saved sessions, providers, and model settings.

For a web-only session, run litespeed serve. For development, use npm run dev from the checkout. See development and updating.

Architecture How it works
Single model One model investigates, implements, and checks the task.
Sidekick Fusion · Recommended A strong driver plans and reviews; a cheaper sidekick keeps context across handoffs.
LiteFusion · Experimental One persistent lead routes 63 task categories to specific models and reasoning levels, with one shared hard/escalation map.
Team Fusion A strong driver assigns fresh cheaper workers, runs independent work in parallel, and verifies the combined result.
Expert Fusion A cheaper driver coordinates fresh strong experts and verifies their work. Independent assignments can run in parallel.

Choose any connected model for each role. An optional Planner model handles Plan mode separately. Litespeed uses your last chosen model arrangement for new sessions across workspaces; existing sessions keep their settings. Cost and quality depend on the models and task. See architecture details and limits.

Shunt sends large reads and routine generation to a separate model. Off by default; enable it in Advanced settings during setup or in Models, in either client. How it works and measured results.

Session goals (/goal) keep an objective moving across turns. There is no turn limit unless you set one. Context compaction makes room during long tasks automatically.

Approved commands run with your local user’s capabilities; permissions are not a sandbox. Keep the server local. Provider keys stay server-side, and provider usage may incur charges.

Litespeed is licensed under Apache-2.0. Bundled themes and fonts retain their original licenses; see third-party notices.

── more in #ai-agents 4 stories · sorted by recency
── more on @berriai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/litespeed-a-local-co…] indexed:0 read:4min 2026-09-17 ·