Repository navigation
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 kith to 📦 Packages, placed alphabetically ahead of the existing entries.
markdownlint-cli README.mdis clean locally.LangGraph usage (per the "verify the project uses LangChain/LangGraph" requirement): the library ships
kith.integrations.langgraphwith two primitives —observe_node()wraps any graph node so its outcome (including exceptions, which re-raise unchanged) becomes a recorded observation, andKithSupervisorselects workers by derived reliability and renders a briefing for the supervisor prompt. It's integration-tested against a realStateGraphon langgraph 1.2.x, not just documented. (Note for others hitting this: LangGraph node names can't contain:, so principal ids likeagent:coderneed a node-name mapping — that's in the adapter docstring.)What it does that isn't already in the list: it stores relationship state between agents rather than facts — per-observer observations about other principals, from which trust / reliability / sentiment are derived with decay and provenance. The seeded benchmark in the repo cuts repeat-delegation failures ~82% by consulting that view before routing.
It was recently listed in Awesome-Agent-Memory if a second opinion is useful. Happy to reword, shorten, or move the entry.