Loki Mode

Loki Mode

Your agent says done. Loki proves it: an autonomous coding agent that turns a task or issue into a verified pull request with a signed receipt you can check yourself.

Website | Quickstart | Install guide | User guide | CLI reference | Compare with opencode | Changelog

The npm badge above tracks the current release; see CHANGELOG.md for release notes.

CLI reference: docs/CLI-REFERENCE.md (generated from the command registry).

Install

npm install -g loki-mode

The npm package installs the Bun runtime the engine needs as an optional dependency. Other ways in: bun install -g loki-mode, brew tap asklokesh/tap && brew install loki-mode, or docker pull asklokesh/loki-mode:latest (Docker guide). Upgrade with loki self-update.

Want to see a result before you install or spend anything?

npx loki-mode start   # no git repo: a real receipt, no key, no spend

npx loki-mode tour # the same receipt when you are already inside a repo

npx downloads the package the first time, so that step needs the network. The receipt itself replays offline and checks with no provider and no key.

npx loki-mode wow     # a provider is ready: one tiny real task in a temp repo, its own receipt

First run

Loki needs a model. Claude Code (claude) is the default provider: install it and log in. The bundled Agent SDK with an ANTHROPIC_API_KEY can stand in for the CLI on the main path. Other coding CLIs are optional. See Requirements.

cd your-repo

loki setup # first-run wizard (or: loki doctor --fix) loki start "add rate limiting to /api/login" # the primary path: build, verify, seal a receipt, open a PR loki start prd.md # same, from a PRD file loki start owner/repo#123 # same, from a GitHub, GitLab or Jira issue loki "fix #123" # an issue of this checkout; a copied issue or PR URL works as is loki edit "rename fooBar to foo_bar" # one small change, no loop loki chat # interactive alternative: Plan and Build modes

loki start, loki " ", loki owner/repo#N and loki quick " " all run on the Loki 10 engine by default, whatever the flag order or input form. Add --no-pr to build and verify without opening a pull request, --max-cost to cap spend, and --provider to pick another coding CLI. The spend cap defaults to $100 when ANTHROPIC_API_KEY or OPENAI_API_KEY is set and to no dollar cap on a subscription login; budgets.per_run in loki.yaml also sets it. Inspect the route without running: loki route start prd.md or --explain-route. New here? The 5-minute quickstart walks through it.

What you get

Every run starts from a delivery contract derived from your task, writes checks from the task alone before touching code, implements, verifies, and ends in exactly one outcome: VERIFIED, ALREADY_SATISFIED, FAILED, BUDGET_STOP, BLOCKED or STALLED (exit codes). If the contract cannot be satisfied as written, the run stops and asks one question instead of guessing.

• A pull request written for a quick review: what the issue asked, what changed, how it was tested, and what was NOT PROVEN. A VERIFIED run opens a ready PR; a PARTIAL run opens a draft PR titled [PARTIAL] that leads with what is not proven; any other outcome keeps the branch local and prints where it is.
• A signed receipt at .loki/runs/ /receipt.json, signed with a local Ed25519 key created on first run.
• A specialist review when the review council runs: it selects reviewers from a specialist pool (agents/types.json, scored by run.sh:FOCUS_KEYWORDS) by matching the changed files and diff against each reviewer's keywords.

loki verify              # newest run; or: loki verify <run-id>

loki verify re-hashes the receipt, checks its signature and checks it against the run's event log. It prints a verdict and exits 0 (VERIFIED), 1 (TAMPERED), 2 (UNCHECKED), 3 (UNSIGNED, refused unless --allow-unsigned), 4 (run outcome not verified) or 66 (no runs); [ $rc -eq 0 ] is the only safe test for "verified". It also checks that your checkout still matches the sealed code: a run that opened a PR returns you to your starting branch, so verify it from the run's branch (git fetch origin loki/ && git checkout --detach FETCH_HEAD), or it reads UNCHECKED and says so. loki start also requires fail-to-pass for a declared behavior change: a Wall test must fail on the old code and pass after, or the verdict stays PARTIAL (LOKI_MUTATION_STRICT=0 opts out). Full table: docs/exit-codes.md. On another machine, export the public key with loki keys export and pass it with loki verify --pubkey . A receipt claims only what its checks ran, and lists what they did not; signing proves who produced it, not that the code is bug-free. Details: docs/SIGNED-RECEIPTS.md.

For a multi-repo change set, loki start --workspace " " seals one signed composite.json over every child receipt, and loki verify /composite.json re-checks it offline (docs/WORKSPACES.md). A composite never reads higher than its weakest child.

Two vocabularies, not one. Receipt verdicts (sealed, 5): VERIFIED, PARTIAL, ALREADY_SATISFIED, SPEC_CONFLICT, FAILED. Run outcomes (printed, 8): VERIFIED, ALREADY_SATISFIED, PARTIAL, FAILED, BUDGET_STOP, BLOCKED, STALLED, CANCELLED. BUDGET_STOP, BLOCKED, STALLED and CANCELLED are run outcomes, never receipt verdicts.

Composite: every child VERIFIED or ALREADY_SATISFIED gives VERIFIED (all ALREADY_SATISFIED stays ALREADY_SATISFIED, any SPEC_CONFLICT child keeps SPEC_CONFLICT); one PARTIAL child caps it at PARTIAL; a FAILED child fails it. loki verify on a composite exits 0 VERIFIED, 1 TAMPERED, 2 UNCHECKED, 3 UNSIGNED.

Autonomy and deploy: .loki/policies.json autonomy: propose|execute|operate governs what loki start may do (propose opens nothing, execute opens a PR, operate also allows deploy); no file keeps today's behavior. loki trust prints advisory graduation advice from your receipts and never writes the policy. Loki deploys only behind loki deploy --execute (or loki start --deploy) plus a VERIFIED, HEAD-anchored receipt and the policy permission; --health-url and --auto-rollback add a post-deploy probe and a documented provider rollback. A Sentry alert webhook can enqueue a receipt-gated fix PR (docs/sentry-intake.md).

A finished run prints a short summary (every run on both engines also ends with a unified Result, Files, Cost, Elapsed, Receipt and next: block; --quiet prints only that block, --json adds a summary object):

Outcome:    VERIFIED

PR: https://github.com/owner/repo/pull/1 Receipt: sha256:2f9a41c7e0b3... NOT PROVEN: full suite, app boot, security scan Cost: $0.42 (claude, 212k tokens) Time: 4m12s (intake 11s, plan 20s, implement 3m10s, verify 31s)

Core commands

Core verbs: docs/CLI-CORE-VERBS.md. Every command (generated): docs/CLI-REFERENCE.md. Engine guide, provider table, model routes, custom agents and chat: docs/v10/GUIDE.md. Honest comparison with opencode: docs/COMPARE-OPENCODE.md.

Models, providers and local models

Two providers are supported. Claude Code is the default Tier-1 provider (the claude CLI, or, with only ANTHROPIC_API_KEY, the Anthropic Agent SDK). --provider opencode (or LOKI_PROVIDER=opencode) runs opencode, which reaches any model, including OpenRouter: export OPENROUTER_API_KEY and pass --model openrouter/ / ; the Loki 10 engine enforces the wall-clock limit and a post-iteration guard scan there. codex, cline, aider and gemini were removed and exit 2 with a one-line migration message. To keep the Claude harness on OpenRouter or a local model, set LOKI_MODEL_ROUTE= / (kinds: openrouter, ollama, lmstudio, llamacpp, vllm, custom) before loki start; loki models --local finds local runtimes and prints ready-to-paste values.

LOKI_MODEL_ROUTE=ollama/qwen3-coder loki start prd.md

OPENROUTER_API_KEY=sk-or-... loki start --provider opencode --model openrouter/deepseek/deepseek-v3.2 prd.md

Control Plane

A local UI and API for all yo