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
- Dev hacks reMarkable e-ink tablet to let Opus draw and animate — Stefania_druga · 2026-10-26
- Godot games are trivially decompilable — compile C# to native DLL for real protection — mflux · 2026-10-26
- Techhalla shares full 2D-to-3D workflow with Opus 5.5 and Kling 4.0 prompts — techhalla · 2026-10-26
- Jason Furman: Building Econvitals pre-AI would need ~50 people, 3 years, $20M — HarrySurden · 2026-10-26
- Dev dictates to Claude Code for 4+ hours while riding indoor bike in aero position — jacob_posel · 2026-10-26
- Proxmox and LXCs are underrated in the age of AI agents — basedjensen · 2026-10-26