MlkBlk-IT /

icy-loom

Hybrid MCP gateway for local and cloud LLM workflows: cache, context drawer, tool relay and SQLite ledger. CPU-first and provider-flexible

A new way for AI to search for data
View on GitHub
1GitHub stars

What XERJ indexed

Snapshot

Whole repository

The whole repository at commit 56c529b1cb.

Selected work

Malik Belkacemi
@MlkBlk-IT

Licence

The repository

MIT

LICENSE file checked at the pinned commit; the author agreed to inclusion.

The XERJ corpus

MIT, with credit

The owner added it on hub.xerj.org after signing in with GitHub, on 2026-11-01. Same terms as the repository. Answers name the repo, the commit and the file:line.

selected for the XERJ Corpus Hublicence clearedsuggested use: adapt with attribution

context-compressionllm-cachelocal-firstmcpmcp-serverpythonself-hostedsqlite

Example questions

The prompt

Paste it into your AI agent. It clones MlkBlk-IT/icy-loom at the pinned commit and indexes it on your machine.

Search the GitHub repository MlkBlk-IT/icy-loom with XERJ (https://hub.xerj.org/corpus/mlkblk-it--icy-loom).
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/MlkBlk-IT/icy-loom icy-loom && git -C icy-loom checkout 56c529b1cbccb2c184aced63836c2c50002ad9f5
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./icy-loom --url http://127.0.0.1:9200 --prefix icy-loom --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

Malik BelkacemiAI, prompts and agents corporadunorth595--ai-agent-memorydunorth595--ai-agent-chatlokdocsqrroian6/apple-health-ai-bridgesandbaseai/sandbase-harnessdziksu/synkinema

Selected work and consent: the XERJ registry.