Add errlore (failure-memory SDK for agents)#274
Open
Ma4etaSS wants to merge 1 commit into
Open
Conversation
|
We require contributors to sign our Contributor License Agreement, and we don't have @Ma4etaSS on file. You can sign our CLA at https://e2b.dev/docs/cla . Once you've signed, post a comment here that says '@cla-bot check' |
Author
|
@cla-bot check |
|
The cla-bot has been summoned, and re-checked this pull request! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 errlore, kept in alphabetical order (between Chidori and Fixie), in the existing entry format.
errlore is a small SDK that gives an AI agent a memory of its own failures: every resolved error becomes a lesson injected into the next similar prompt, with per-model KNOWN ISSUES warnings and a reinforce/decay loop that tracks whether a lesson helped. Embedded and file-based (JSONL + file locks), offline, no server, no API keys, MIT.
Complements the debugging/monitoring SDKs already listed — it is the learn-from-failures layer. Paired A/B benchmark with committed raw outputs is in the repo.
Thanks for the list!