Autonomous spec-to-product coding-agent CLI with an MCP server exposing 34 tools over stdio.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag β we're steadily working through the catalog.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
The free, source-available autonomous coding agent by Autonomi. Same Loki CLI, SDK, and MCP for everyone; the commercial editions for teams and enterprises are sold under the Autonomi brand (Autonomi Cloud, Autonomi Enterprise).
Hand it a spec. It does not accept "done" on an empty diff or failing tests.
| Method | Command | Notes |
|---|---|---|
| Bun (recommended) | bun install -g loki-mode | Fastest startup for CLI commands. |
| npm | npm install -g loki-mode | Works without Bun (bash fallback). Migrate any time with loki self-update --to bun. |
| Homebrew | brew tap asklokesh/tap && brew install loki-mode | Auto-installs Bun as a dep. |
| Docker | docker pull asklokesh/loki-mode:latest | Bun + Claude CLI pre-installed. See DOCKER_README.md. |
Upgrade with loki self-update. Long form: Installation Guide.
Adds three slash commands and the Loki MCP server (memory, task queue, code
search, build management) to Claude Code. It calls the CLI rather than bundling
it, so install loki-mode above first. Verify with claude plugin list:
a healthy install reports Status: enabled.
That is the whole happy path. It asks for a one-line idea, picks a template, shows the real cost and time estimate before spending anything, then builds. Press Enter through every step and you get a sample Todo app.
One command, no prompts (CI, scripts, containers, any shell without a terminal):
Both halves are required with no terminal: an idea (or a path to a PRD file)
and an explicit --yes. Given both, Loki picks the top-ranked template
automatically, prints the same honest cost and time estimate, and starts the
build without asking anything. Missing either half exits 2 with the
needs-a-terminal message and writes nothing, so an ambient LOKI_AUTO_CONFIRM
or a stray argument in CI can never start a paid build on its own. Existing
files are never overwritten: if prd.md is present the PRD lands at
prd-quickstart.md, then numbered suffixes as needed.
Choose an exact shipped starter when the top-ranked match is not the one you want:
Template discovery works without a terminal or provider and lists every shipped
starter's stable name and purpose in catalog order. It returns before estimation,
consent, PRD writes, or build execution. Positional input and execution/preview
flags are intentionally incompatible; --json is the only optional modifier.
--template accepts an exact template name for idea inputs and works the same
way with interactive use or --dry-run (including JSON preview). Unknown
templates, duplicate flags, and combinations with a PRD path refuse before
provider discovery, estimation, writes, or build execution.
Preview the same deterministic template choice and estimator-backed plan with zero writes or execution:
Preview requires an idea or readable PRD path, works without a terminal or AI
provider, and exits before creating a PRD or starting a build. --dry-run and
--yes are mutually exclusive so execution intent is never ambiguous.
For scripts and local dashboards, add --json to receive one versioned JSON
object instead of terminal text:
The object contains the input kind, deterministic selected template (or null
for an existing PRD), the exact estimator response under plan, and a bounded
continuation containing the exact idea/template or the PRD path and SHA-256.
--verify-preview validates the same bounded duplicate-key-rejecting schema and
requires either a currently shipped idea template or the unchanged digest-bound
PRD, while emitting no idea or PRD path. It accepts a file or piped stdin and
returns before provider discovery, estimation, writes, or build execution.
--from-preview requires explicit argv --yes, rejects malformed, conflicting,
symlinked, or changed inputs before provider and build boundaries, then uses the
existing no-clobber quickstart path. The saved plan is evidence rather than
execution authority: Loki recomputes and displays the current estimate before
starting. --json requires --dry-run; invalid input or estimator failure
writes no JSON, and preview still exits before provider discovery, file writes,
or build execution.
Or go straight at it:
Loki needs a model to drive. An ANTHROPIC_API_KEY alone is enough (the
Claude Agent SDK ships inside Loki); or point it at Claude Code, aider, cline,
or an open model. Run loki doctor and it tells you exactly what is missing.
Prints a real Evidence Receipt from a past build, headline and all:
"WITH GAPS" is the point. Build was not run, security has findings, and the receipt says so on its own front page. Recompute the diff hash yourself and check it matches -- you are not asked to trust the agent's self-report.
How it works: Drop a spec -- a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. Loki Mode classifies complexity (
run.sh:detect_complexity()), selects reviewers from a specialist pool (agents/types.jsonships 41 role definitions; 10 are keyword-scored by the review selector atrun.sh:FOCUS_KEYWORDS, alongside the mandatory reviewers, and the rest are role descriptions inreferences/agents.mdthat the orchestrator adopts per phase rather than separate processes), with parallel review (blind council) and optional worktree streams on Claude Code, sequential on other providers - and runs autonomous RARV cycles (Reason - Act - Reflect - Verify, seerun.sh:run_autonomous()) with 8 quality gates (seeskills/quality-gates.md). Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.
Self-reported completion is the failure users actually hit. A survey of the open issue trackers of seven coding harnesses (OpenHands, Cline, Aider, SWE-agent, Roo-Code, OpenCode, Continue) found the recurring complaint is the agent silently not doing the work -- "always stuck at Preparing write" (opencode#11112, 76 comments), "Continue not making changes to code" (continue#7143), "Agent does not execute functions" (continue#5696). None of those seven publishes a machine-checkable completion artifact.
We measured every named competitor that ships a local CLI -- opencode 1.18.9,
aider 0.86.2, codex-cli 0.146.0, Claude Code 2.1.220, cursor-agent -- and none
exposes a command that verifies the agent's own output. Rerun it yourself with
bash tests/test-competitor-verify-surface.sh.
That is a measurement of the CLI surface, not of whole products: a web UI or an
API could expose something --help does not, and Devin and Replit Agent ship no
local CLI so they are not covered.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/loki-mode)<a href="https://allmcps.com/mcp/loki-mode"><img src="https://allmcps.com/api/badge/loki-mode?style=directory" alt="Loki Mode on AllMCPs" /></a>