Open Source OpenWiki: A Knowledge Base for Agents
BraceSproul · x · 2026-07-16
The author argues that agents often fail not because of insufficient context, but because the underlying model is too weak. To bridge this gap, they propose using an LLM wiki: structuring codebases, product details, or domain knowledge into a knowledge base that agents can query.
They recently open-sourced OpenWiki, their implementation of this paradigm. The team is also hosting a meetup at their new office to discuss this approach, covering:
- How to actually build and maintain such systems
- Whether the term "wiki" is accurate
- How Cognition built DeepWiki
The event will feature a sharing session by @jacobtpl from Cognition's research and engineering team.
More from coding & agent
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11
- SmolVM open-sources persistent computer infrastructure for agents that outlive chat sessions — aniketmaurya · 2026-09-11
- ARRM targets silent economic regressions in AI agents that functional tests miss — Beautiful_Belt_601 · 2026-09-11
- Dev builds browser 3D pizza delivery game with Claude: physics, GPS pathfinding, traffic AI — vinishkapoor · 2026-09-11
- Build X Carousel Posts from One Wide Image: A Splitter Tool Plus YouMind Skill Workflow — sujingshen · 2026-09-11
- "Anyone still coding the old way?" The joke capturing post-AI programming culture — lxfater · 2026-09-11