Valery Barsukov

What an agent can do with the flai corpus

barval/flai: FLAI is a self-hosted, privacy-first AI platform. Your all-in-one local assistant: smart chat, web search, voice, media generation, and…

• Look up how flai implements docker, docker-compose, piper-tts, with answers cited to file and line.
• Reuse a worked example: the commit “render message media, previews and tasks, and stop the mic…” (4 files · JavaScript, Python).
• Answer from flai's real JavaScript source instead of memory (API design and specification).

• How does flai implement docker?
• What does demo do in flai?

Search the GitHub repository barval/flai with XERJ (https://hub.xerj.org/corpus/barval--flai).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/barval/flai flai && git -C flai checkout 2af99cb568adfe13433dcb170d0ff95218ec63b1
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./flai --url http://127.0.0.1:9200 --prefix flai --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus barval--flai · API design and specification
Related corpora: ann-benchmarks, dunorth595--ai-agent-chat, DigitalJacob/booking_bot, sheikhayaan/AUTOPR
Search an OpenAPI spec from an agent · Case study: reference coding for agents