little-coder

Coding agent tuned for small local models, built on the pi agent harness and run from the terminal.

IndexedApache-2.0★ 2,701

Chalk Labs

Need help deploying little-coder?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Get started

Setup steps are in the repository. Website · Repository

About

little-coder is a coding agent tuned for small local models and built on top of the pi agent harness. It bundles about 30 extensions, 30 skill markdown files and a Python benchmark harness, and its launcher runs pi with that fixed set of extensions. The default setup uses a local llama.cpp server hosting Qwen3.6-35B-A3B, and it can also run Anthropic, OpenAI, Ollama or LM Studio models. Its plan mode asks clarifying questions and writes a plan for approval before any edits, and the installer requires Node.js 22.19 or newer.

Use cases: coding, code-generation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Jobs: codingREADME
Autonomy: Supervised: runs multi-step tasks, asks at checkpointsREADME
Where you use it: TerminalREADME
Hosting: You run itREADME
Models: llama.cpp, qwen, anthropic, openai, ollama, lm-studioREADME
Interfaces: agent-skillsREADME
Open source: Yes

Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.

Built on

Frameworks named in its dependency files.

0.867score
Pi Agent Core
Earendil
Minimal TypeScript agent harness with an agent runtime, multi-provider LLM API, terminal UI and coding agent CLI that users extend themselves.
HarnessAFreshness: A★ 117.6K↓ 5.1M/wk

Signals

Stars: 2,701
Forks: 186
Open issues: 6
Last commit: Sep 18, 2026 (1 month ago)
Last release: Sep 18, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/itayinbarr/little-coder
Website: itayinbarr.github.io/little-coder/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: README github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get little-coder running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying little-coder?

Call Get help

Cite this page

little-coder. Agent Mart. https://agentmart.dev/agents/little-coder (last updated 2026-10-24)