[Docs] OpenWiki influence study; file improvements #101-#105 - #11
Merged
Conversation
Study of langchain-ai/openwiki v0.2.0 (d4e94ab). Three High Priority items target the prompt/feedback edges of the distillation pipeline: explicit no-op permission in extraction prompts (#101), corrective warnings in store_extraction responses (#102, converges with the same-day OKF study's #97 — implement as one feature), and a user-authored extraction brief (#103). Medium: AGENTS.md marker block (#104), DB permission hardening (#105), and a priority bump for #79 (third independent repo shipping untrusted-data framing).
codenamev
force-pushed
the
worktree-study-openwiki-2026-07-16
branch
from
July 16, 2026 21:10
7e005dc to
063597f
Compare
codenamev
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Study of langchain-ai/openwiki v0.2.0 (commit d4e94ab) via
/study-repo— LangChain's DeepAgents wiki generator, 11.8k stars three weeks after launch.OpenWiki is the same mission approached from the opposite direction: the LLM authors prose pages while a deterministic harness enforces every invariant (write confinement, two-tier no-op detection, post-write validation with corrective feedback injected back into the agent loop, machine-owned indexes). The storage model is rejected (prose has no truth maintenance or row provenance), but the harness patterns target problems we have open.
Changes
docs/influence/openwiki.md(new) — full analysis with file:line evidence, comparison table, adoption opportunities, and rejected features. Cross-linksdocs/influence/okf.md(OpenWiki's frontmatter follows the Google Knowledge Catalog OKF schema that PR [Docs] OKF (Open Knowledge Format) study; improvements #96-#98 #10 studied).docs/improvements.md— new dated section with items #101–#105 plus a priority bump for #79; header + sources updated, merged with the OKF study's same-day header entry.Filed improvements
store_extractionresponses — converges with OKF study #97 (two studies independently filed the same tool-border feedback loop; implement as one feature)Each High item was verified against current ClaudeMemory source before filing (e.g. confirmed
Publish#should_write?already matches their content-hash gate — validation, not adoption — and confirmed the silent reclassification atmanagement_handlers.rb:42).Notes
Docs-only change; no runtime surface. Pre-commit hook chain passed.