asasemahmed /

FullDots

AI coworkers with their own computers. Local-first and self-hosted: bring any model, connect MCP tools with browser sign-in, and approve…

A new way for AI to search for data
View on GitHub
3GitHub stars

TypeScript

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 779477263e (2026-10-17).

Selected work

Nommoh Hayab
@naet001

“Export a conversation as Markdown from the sidebar menu”. 19 files, 647 lines in tests, src/server, src/client.

Licence

The repository

MIT

Checked by a person at the pinned commit.

The XERJ corpus

MIT, with credit

The author agreed by email on 2026-10-21. Same terms as the repository. Answers name the repo, the commit and the file:line.

in licence reviewnot in the hub yetsuggested use: adapt with attribution

ai-agentscomputer-usellmlocal-firstmcpreactself-hostedtypescript

Example questions

The prompt

Paste it into your AI agent. It clones asasemahmed/FullDots at the pinned commit and indexes it on your machine.

Search the GitHub repository asasemahmed/FullDots with XERJ (https://hub.xerj.org/corpus/asasemahmed--fulldots).
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/asasemahmed/FullDots FullDots && git -C FullDots checkout 779477263e3068075a281f524253f7b226915f44
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./FullDots --url http://127.0.0.1:9200 --prefix fulldots --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.

Related

Nommoh HayabAI, prompts and agents corporaatoma-run--atomaagentscopeesbuildgeorgevibing/conch-agentCubinghackerz/ai.diyholt-os/holt

Selected work and consent: the XERJ registry.