Add Loki Mode under Orchestrators and autonomous loops#121
Open
asklokesh wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Loki Mode to the "Orchestrators & autonomous loops" section, placed by star count (971) between loom (1.3k) and Bernstein (559), matching the section's "Sorted by GitHub stars" convention. Entry uses the section's star-badge + separator format to stay consistent with neighboring entries.
What it is: a source-available (BUSL-1.1), CLI-first autonomous coding agent that takes a spec (PRD, GitHub issue, OpenAPI doc, or a one-line brief) toward a deployed product.
Why it fits the section and the inclusion criteria:
loki start ./prd.md,loki heal <path>, etc.What makes it distinct from existing entries: an explicit completion-verification gate. Most agents end a task on the model's self-report. Loki runs a blind-review completion council plus an evidence gate that can veto "done", so it keeps working (or asks for input) until the evidence is actually there.
Other specifics: brownfield/legacy healing via
loki heal; local-first with your own API keys (no data egress); ships a 26-tool MCP server; reads AGENTS.md at the repo root. Provider-agnostic (Claude Code, OpenAI Codex CLI, Cline, Aider).Reproducible benchmark (available if useful, not led with): 98.78% on HumanEval (162/164), reproducible from the repo via
benchmarks/run-benchmarks.sh humaneval --execute --loki.Checked for duplicates: Loki Mode is not currently listed.