A workbench, not a portal.

Your models.Your tools.On your machine.

A local-first AI coding workbench. Native terminal REPL, browser admin. Wire up your own local runtime or your API keys — no bundled model, no uploaded sessions, no account. Each session closes cleanly and leaves the next starting point.

Get started Open issues →

GPL source
npm package
Local-first
Native REPL

owlcoda · session 7e3a~/work/owlcoda

$ owlcoda

# 42+ tools, 69+ slash commands, your config

Readsrc/native/conversation.ts412 lines · 13.2 KB

Grep"completion-guard" → 6 matches3 files

Editsrc/native/completion-guard.ts3 hunks proposed

Bashnpm test --silent14 passed · 2.1 s

✓ patch applied · vitest 14/14 · session saved.

owlcoda admin · models

BROWSER ADMIN · FIRST-RUN CONFIGURATION

Ollama (local)http://127.0.0.1:11434/v1wired
Kimi Codinghttps://api.kimi.com/coding/v1wired
OpenRouterhttps://openrouter.ai/api/v1check

In five seconds

A local-first AI coding workbench.

Runs onyour machine. Node 20.19+ CLI, native terminal REPL, no hosted server.
Connects toyour local runtime (Ollama, LM Studio, vLLM) or your cloud API key.
Leaves behindtranscript · session JSON · tool evidence · context budget · follow-ups.
Belongs tothe local-first Owl stack. Public GPL source plus npm install path. No account, no server.

Quickstart

Install from npm. Read the source on GitHub.

OwlCoda installs from npm and publishes its GPL source on GitHub. Configure your own local runtime or cloud provider in Admin.

Run once

npm install -g owlcoda@latest

Node ≥ 20.19
npm package
GPL source
local logs only

Step by step

01
Install the npm package
```
npm install -g owlcoda@latest
```

Verify the global command

which owlcoda
npm ls -g owlcoda --depth=0
owlcoda --version

03
Configure providers in the browser admin
```
owlcoda admin
```
04
Start the REPL
```
owlcoda
```

Bring your own backend

OwlCoda doesn’t ship a model. You point it at one.

Wire up local runtimes, your cloud API keys, or both. Endpoint and provider probes treat them with one mental model.

BackendKindEndpointWire formatStatus

OllamaLocalhttp://127.0.0.1:11434/v1OpenAI-compatible · everyday local routeauto-detect

LM StudioLocalhttp://127.0.0.1:1234/v1OpenAI-compatible · GUI runtimeauto-detect

vLLMLocalhttp://127.0.0.1:8000/v1OpenAI-compatible · GPU runtimeauto-detect

Custom localLocaluser-suppliedOpenAI-compatible · any /v1 endpointauto-detect

Kimi CodingCloudhttps://api.kimi.com/coding/v1provider-native · kimi-for-codingtested

Kimi (Moonshot)Cloudhttps://api.moonshot.ai/v1OpenAI-compatible · generic MoonshotBYO key

MiniMaxCloudhttps://api.minimaxi.com/anthropicMessages-shaped · Anthropic-styletested

OpenRouterCloudhttps://openrouter.ai/api/v1OpenAI-compatible · multi-upstream catalogBYO key

Bailian / DashScopeCloudhttps://dashscope.aliyuncs.com/compatible-mode/v1OpenAI-compatible · Alibaba-hosted modelsBYO key

OpenAI-compatibleCloudhttps://api.openai.com/v1OpenAI-compatible · any /v1 vendorBYO key

Native REPL

The terminal is the product.

OwlCoda runs as a native terminal REPL — not a web wrapper. Selection-first transcript, real shell tooling, persistent sessions.

42+ tools Bash, Read, Write, Edit, Glob, Grep, Task, MCP-served tools, agent dispatch, scheduling, plugins.
69+ slash commands Inspect models, costs, budgets, context, sessions, skills, training — all from the same prompt.
Selection-first transcript Drag-select and copy work the way they do in any other terminal app.
Persistent sessions Every conversation lands under ~/.owlcoda/sessions/ and resumes with --resume <id>.
Sustained-runtime budget gate Long runs are checked against a context budget so a finished report can’t be silently truncated.

Slash commands · selected from 69+

/modelList configured models, switch active route.
/budgetInspect context budget and per-run caps.
/contextPrint current context window state.
/sessionsBrowse and resume saved sessions.
/resumeResume a previous session by id.
/trainingScore and export sessions for fine-tuning.
/traceOpen the trace inspector for the last run.
/perfShow per-tool latency and token spend.
/doctorProbe routes, keys, and runtime health.
/toolsList available tools, scoped or global.
/skillsManage learned skills and their triggers.
/tokensPer-message token accounting.
/costSpend by provider for the current session.
/configShow or edit ~/.owlcoda/config.json.
/agentsList available subagents and dispatch one.
/planEnter plan mode for multi-step work.
/clearClear the visible transcript (keep session).
/undoRoll back the last tool-applied change.
/openOpen admin UI route from the REPL.

owlcoda · session 7e3a~/work/owlcoda

$ /model

default → qwen3-coder (ollama · local)

heavy → kimi-for-coding (kimi · provider-native)

long-context → minimax-m27 (minimax · messages)

cheap → openrouter/auto (openrouter)

$ /model heavy

✓ active route → kimi-for-coding · ctx 128k · key from env.

$ patch the completion-guard false positive

Readsrc/native/conversation.ts412 L · 13.2 KB

Grep"completion-guard" → 6 matches3 files

Globsrc/native/**/*.ts47 paths

Editsrc/native/completion-guard.ts3 hunks proposed

Bashnpm test --silent14 passed · 2.1 s

Taskspawn review-agentin-progress

✓ patch applied · vitest 14/14 · session saved.

Browser admin

Configure once. Close the tab. Start working.

owlcoda ui prints a one-shot admin URL. Add --open-browser to launch it. owlcoda admin is an alias. The admin is for first-run configuration — advanced catalog, aliases, and orphans live behind Diagnostics.

01
Print URL
owlcoda ui prints a one-shot localhost URL bound to a session token. Open it manually, or pipe it into your launcher.
02
Open browser
owlcoda ui --open-browser hands the URL straight to your default browser.
03
Configure
Add a provider, paste an API key, run a test connection. The page closes itself when you’re done.

$ owlcoda ui
$ owlcoda ui --open-browser
$ owlcoda admin

Catalog, aliases, and orphan cleanup are tucked under Diagnostics. The first-run path stays calm.

owlcoda admin · providers · kimi-coding

01Wire

02Test

03Save

PROVIDER · KIMI CODING

ProviderKimi Coding

Endpointhttps://api.kimi.com/coding/v1

Backend modelkimi-for-coding

API keysk-•••••••••••••••

Wire formatprovider-native

Test200 OK · 412 ms

No port hardcoded. The URL changes per launch and never leaves your machine.

Coda

A coda is not just an ending. It is the closing passage that leaves the next starting point.

Every ending should leave a next starting point.

Each finished session writes a small artifact trail under ~/.owlcoda/. Resume work tomorrow from that trail, not from a chat window.

$ owlcoda --resume <id> # pick the next starting point.

~/.owlcoda/sessions/7e3a-…closed · 2026-04-21 18:42

~/.owlcoda/sessions/<id>.jsonsession record · model · routes
~/.owlcoda/sessions/<id>/transcript.mdhuman-readable transcript
~/.owlcoda/sessions/<id>/tool-runs.ndjsontool evidence · diffs · output
~/.owlcoda/sessions/<id>/context.mdcontext · budget state
~/.owlcoda/sessions/<id>/followups.mdopen follow-up tasks
~/.owlcoda/training/<id>.jsonloptional training export · opt-in

Privacy posture

No account. No server. No hosted telemetry pipeline.

No accountThere is no OwlCoda account. There is no OwlCoda server.
Local diagnosticsSessions stay on your machine. Readiness events are local JSONL files, and outbound calls are the backends in your config.
Your configAll config and sessions live under ~/.owlcoda/, owned by you, in plain JSON and Markdown.
Your training dataTraining-data collection is opt-in and PII-sanitized before disk write.

Owl stack

OwlCoda is the first public product in a local-first Owl stack.

Future Owl tools will share the same posture: local-first, transparent, your machine, your data. Nothing here is portal-marketing.

OwlCodasource · v0.18
AI coding workbench. Native REPL plus browser admin. Install from npm; inspect the GPL source on GitHub.
owlmlxreserved
Future local learning runtime foundation for training data, adaptation, and runtime-truth registration.
owlopsreserved
Local-first ops automation. Reserved for a later public release.