OpenWiki 0.2 is adopting the OKF spec
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
OpenAI is lying
Theo - t3․gg
81.9k views
Oh No, Tim Miller is Streaming Again
The Bulwark
57.5k views
Open source is dying
Theo - t3․gg
97.8k views
The situation is escalating.
Adam Mockler
196.1k views
Trump 2.0 is Trashing Sarah M's Love Life
The Bulwark
71.5k views
She is the Most Annoying Loser
penguinz0
334.8k views
OpenAI Is A Ponzi Scheme
ThePrimeTime
86.7k views
Austin Reaves Is Proving He's THE GUY For The Lakers!!
The Arena
147.4k views
OpenAI is burning cash
Theo - t3․gg
81.8k views
OpenAI’s TikTok Clone Is Interesting…
Theo - t3․gg
47.3k views
Top Comments (8)
We've needed structured metadata for agent retrieval for a while. Type, title, and tags as first-class attributes should have been the baseline from the start.
Thanks for Adopting the OKF, i was torn between OKF and openwiki, do we have any recommended models to be use with openwiki ? any benchs or evals done ?
Isnt this a bit similar to obsidian? With the frontmatter and the node graph?
Is a byok the only way to use openwiki? I pay for Claude code. Cant I use it as a skill and thereby use the Claude code model in use?
Using OKF for deterministic tag filtering is a huge step up, but relying on flat metadata still misses the actual logical relationships between concepts. If you evolve this into a 'FileGraph' by baking rich semantic edges (Depends_on, Contradicts, Supersedes, Adds_Details, ... ) directly into the YAML and traversing them via an in-memory graph, agents can instantly navigate complex technical prerequisites, preserving perfect semantic coherence from digestion to context generation.
OKF is awesome
pity ... Omg my PACT & SPARC use templates to make what I exactly need. How many months do you need to understand that it's better than your RandomWiki?
Funny how the one lib that's doc sucks the most talks about docs the most
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (8)
We've needed structured metadata for agent retrieval for a while. Type, title, and tags as first-class attributes should have been the baseline from the start.
Thanks for Adopting the OKF, i was torn between OKF and openwiki, do we have any recommended models to be use with openwiki ? any benchs or evals done ?
Isnt this a bit similar to obsidian? With the frontmatter and the node graph?
Is a byok the only way to use openwiki? I pay for Claude code. Cant I use it as a skill and thereby use the Claude code model in use?
Using OKF for deterministic tag filtering is a huge step up, but relying on flat metadata still misses the actual logical relationships between concepts. If you evolve this into a 'FileGraph' by baking rich semantic edges (Depends_on, Contradicts, Supersedes, Adds_Details, ... ) directly into the YAML and traversing them via an in-memory graph, agents can instantly navigate complex technical prerequisites, preserving perfect semantic coherence from digestion to context generation.
OKF is awesome
pity ... Omg my PACT & SPARC use templates to make what I exactly need. How many months do you need to understand that it's better than your RandomWiki?
Funny how the one lib that's doc sucks the most talks about docs the most