Nano-Collective/nanocoder

An open coding agent for your terminal, built by a community collective rather than a company. Bring your own model, keep your code on your machine, and owe nothing to anyone.

What it solves

Nanocoder is an open-source, privacy-respecting coding agent that allows developers to perform agentic coding directly from the terminal. It eliminates vendor lock-in by allowing users to bring their own AI models (local or cloud-based) and ensures that code remains on the local machine.

How it works

It operates as a CLI tool that can be run in either a fullscreen interactive mode or an inline mode. Users can specify a provider (such as Ollama for local models or OpenAI-compatible APIs like OpenRouter and Anthropic) and a model to execute coding tasks. It supports various development modes (normal, auto-accept, yolo, plan, architect) and specialized commands for reviewing branches or PRs and opening PRs in isolated worktrees.

Who it’s for

Developers who want a local-first, open-source AI coding assistant that gives them full control over their data and the AI model provider they use.

Highlights

  • Multi-provider support: Works with local models via Ollama or any OpenAI-compatible API.
  • Privacy-focused: Local-first approach with no paid tiers or telemetry.
  • Terminal-native: Offers both fullscreen and inline rendering modes for a seamless CLI experience.
  • Advanced Git integration: Includes capabilities to review PRs and manage coding sessions in isolated Git worktrees.

Related

  • Project
    anomalyco/opencode

    OpenCode is an open-source AI coding agent available as a CLI and a beta desktop app. It installs via curl script, npm, Homebrew, pacman, mise, or Nix. It includes two built-in agents — "build" (full-access, default) and "plan" (read-only) — switchable with Tab, plus a "general" subagent. Docs are at opencode.ai/v2/docs, and projects using "opencode" in their name must disclaim affiliation with the team.

  • Project
    PawanOsman/OpenCursor

    OpenCursor is an open-source AI coding agent for VS Code that allows developers to integrate various cloud or local models to automate coding tasks, file edits, and terminal operations with full review control.

  • Project
    StartupHakk/OpenMonoAgent.ai

    OpenMono Agent is a self‑hosted AI coding assistant built on .NET 10 and llama.cpp. It runs entirely on the user’s hardware (GPU, AMD iGPU, or Apple Silicon), offering a full agentic loop with 21 sandboxed tools, deep Roslyn‑based code intelligence, vision, private web search, and VS Code integration. After a one‑command install, the model runs locally for free, eliminating cloud subscriptions and per‑token fees.

  • Project
    nanobrowser/nanobrowser

    Nanobrowser is an open‑source Chrome/Edge extension that lets a large‑language‑model act as a user inside your browser. You type tasks in a side‑panel; the agent reads pages, clicks, types, navigates tabs, and can upload/download files. It supports many cloud LLM providers and local models (via Ollama, LM Studio, etc.), offers Ask/Auto modes, per‑site permissions, voice input, memory, and multi‑tasking, all while keeping API keys and page data private. Install from the Chrome Web Store or build from source with Node 24 and pnpm 10.

  • Project
    ConardLi/easy-agent

    Easy Agent is a terminal‑based AI coding assistant that can read, edit, and run code under configurable permission rules and optional OS sandboxing. It supports major LLM providers, offers persistent sessions, extensibility via plugins/skills, and multiple safety modes (plan, auto, default). Install via npm, trust a workspace, then interact with the REPL to ask questions, make multi‑file changes, run tests, and undo actions.