Malik Belkacemi
Malik Belkacemi's work was selected for the XERJ Corpus Hub, the open reference memory AI coding agents search before they write code. When an agent meets the same problem, it gets this implementation back as a worked example, with the author and the repository attached.
Totals across every corpus @MlkBlk-IT appears in; a commit selected for two corpora counts once. Files and lines count the selected commits; each corpus indexes the whole repository at its pinned commit.
What an agent can do with the icy-loom corpus
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
- Look up how icy-loom implements context-compression, llm-cache, local-first, with answers cited to file and line.
- Answer from icy-loom's real source instead of memory (AI, prompts and agents).
- How does icy-loom implement context-compression?
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.
corpus mlkblk-it--icy-loom · AI, prompts and agents
Related corpora: dunorth595--ai-agent-memory, dunorth595--ai-agent-chat, roian6/apple-health-ai-bridge, sandbaseai/sandbase-harness
AI search and retrieval with XERJ · Case study: reference coding for agents
Selected work
MlkBlk-IT/icy-loom
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
MlkBlk-IT/icycache
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
MlkBlk-IT/mcp-loom-mcp
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
MlkBlk-IT/Mcp-QadGraph
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
MlkBlk-IT/MlkBlk-IT
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
MlkBlk-IT/osiris
The corpus is the whole repository at the pinned commit, not only the files of the selected commit.
Sign in with GitHub or Hugging Face to see more: every selected commit in full (commit date, every folder, licence review state, pin) and the pack builds of each corpus.
[](https://hub.xerj.org/contributors/MlkBlk-IT)
Included with the author's permission (email, 2026-10-31), under each repository's own licence, with attribution. Own more repositories? Sign in with GitHub and add them. Want something removed? Reply to the email, withdraw it on /add, or open an issue on xerj-org/xerj.