OllamaDev CLI is a terminal-native AI coding agent. It talks to Ollama by default — so your code never leaves your machine — and puts 12 backends behind one interface, including Claude, Codex, Gemini and Cursor. Then it adds a parallel crew: research → plan → code → audit → land.
# chat with an agent about the folder you're in (auto-resumes) $ ollamadev # one-shot: describe a change, it edits the files $ ollamadev "add a --json flag to the export command" # the crew: a director plans, N coders build in parallel git # worktrees, an auditor reviews, the winner lands $ ollamadev crew "migrate the config layer to TOML" # commit with an AI message — a leaked secret BLOCKS the commit $ ollamadev ship
A full coding-agent toolkit — not a wrapper. Everything runs locally unless you choose a cloud model.
Runs against Ollama on your own hardware. Offline-capable, no per-token bill, nothing leaves the machine unless you point it at a cloud model yourself.
ollama · claude · codex · gemini · cursor-agent · opencode · qwen · aider · goose · amp · crush · droid. Mix providers inside a single run.
Parallel multi-agent: research → plan → N coders in isolated git worktrees → audit → land. Opt-in brains for routing, debate and amplification.
diff, commit, ship, pr. AI commit messages, and a secret scanner that blocks a commit carrying a leaked credential.
Semantic code index, meaning-based code search, wiki-linked memory, and progressive-disclosure skills.
mcp serve exposes its tools to any MCP client. A built-in LSP gives completion, hover, go-to-def and real diagnostics.
watch re-runs a task on file changes; named long-lived terminals outlive the command and are shared with the desktop app.
eval runs a fixed task suite into a pass-rate you can compare across models — with an exit code you can gate CI on.
One task, a whole bench. Each coder works in its own git worktree, so parallel work never collides — and nothing lands until it's reviewed.
--routeAuto-pick each role's model by task difficulty.
--debateAdvocate / skeptic / judge vote on each changeset.
--amplify NN director plans (keep the modal one) + an N-reviewer audit panel; majority rules.
--dedupeHold coders whose work duplicates another's.
--securityA read-only vulnerability scan into a report.
--reviewHold everything for review instead of auto-applying — accept or discard from the board.
Plain crew is unchanged — every brain above is opt-in.
OllamaDev isn't trying to out-reason a frontier model. It's the local-first layer that unifies your tools — including the cloud CLIs — behind one workflow.
| OllamaDev CLI | A single cloud coding CLI | |
|---|---|---|
| Runs fully local / offline | Yes — via Ollama | No |
| Cost model | Free on local models | Per-token |
| Backends | 12, mixable in one run | One |
| Drives other coding CLIs | Yes — incl. Claude, Codex, Gemini | No |
| Parallel crew in git worktrees | Built in | Varies |
| Raw model capability | Depends on the model you point it at | Frontier |
| Self-hostable & open source | AGPL-3.0 | Proprietary |
Want frontier quality on a specific task? Point a role at a cloud backend — OllamaDev orchestrates it the same way it does a local model.
Needs a C++20 compiler, CMake ≥ 3.21 and Qt6 (Core / Network / Concurrent). No GUI toolchain required.
$ git clone https://github.com/kennethyork/OllamaDev-CLI.git $ cd OllamaDev-CLI $ ./install.sh # build → test → install to ~/.local/bin # or manually $ cmake -S . -B build -DCMAKE_BUILD_TYPE=Release $ cmake --build build -j"$(nproc)" $ ./build/cli/ollamadev --version # package it (.deb / .rpm / .tar.gz) $ cd build && cpack
ollamadev setup — detects your hardware, recommends and pulls a model.
ollamadev doctor — health check · ollamadev backends — which providers are installed.
ollamadev for interactive chat, or ollamadev "your task" for a one-shot turn.
The full surface. Run ollamadev --help for options on any command.
ollamadevInteractive chat, auto-resumes this folder (--new for fresh).ollamadev "<prompt>"One-shot agent turn.backendsWhich providers are installed and how wide they run.models [presets|cloud|chain]List models on the active backend · curated catalog + fallback chain.agents [show <n>]File-defined subagent personas from .ollamadev/agents/*.md.doctorHealth check.setupDetect hardware, recommend + pull a model.pull <model>Download a model (resumable).contextSuggest num_ctx from free RAM/VRAM.statsToken usage for this project.chat ["<prompt>"]Tool-free conversation — no file edits.chat list|delete <id>Manage saved threads.load <id>Resume a specific session.resumePick a recent session to resume.crew "<task>"Research → plan → N coders → audit → land.crew accept|discard <n>Apply held work into your folder, or throw it away.crew steer <n> "…"Talk to a running coder.crew resume [id]Finish an interrupted run; the director re-plans what's left.crew role|packPersonas the director assigns · saved crew configs.boardPending decisions.route [--run] "…"Show (or run) which model the brain picks.index buildSemantic code index (also: status, clear).code-search "<q>"Search the repo by meaning.search "<q>"Web search.skillsProgressive-disclosure skills (list / add / install).memoryWiki-linked notes (new / list / show / graph).diff [--json]The working-tree diff, for review.commit [-a] [-m]AI commit message; a leaked secret blocks it.ship [--yes]Stage → scan → AI commit → ask, then push.pr create|reviewDraft a PR · review one with the model (needs gh).git <sub>status, diff, log, branch, checkout, add, commit, push, pull, stash, show.testDetect and run this project's tests.verify [--max N]Run them, and let the agent fix failures until green.watch "<task>" [paths…]Re-run a task whenever files change.terminal <sub>Named, long-lived ptys shared with the desktop app.evalFixed task suite → a pass rate you can compare.hooksShell hooks on tool/session events; PreToolUse blocks on non-zero exit.commands · /<name>Your own slash commands (prompt templates).mcp serve|list|add|rmExpose the toolset to any MCP client · manage servers.scan [path]Secret scanner (exit 1 on a high finding).lsp [--port N]Language server — completion, hover, go-to-def, diagnostics.config get|set <key>Read/write a dotted config key.completion bash|zsh|fishPrint a sourceable completion script.--coder-backends ollama,claude,codex --coder-models qwen3.5:9b,,