llmslim
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps
What XERJ indexed
Snapshot
The whole repository at commit 333787d3fa (2026-09-22). main is 273 commits ahead.
Selected work
“make v0.6.0 playground adaptive”. 8 files, 664 lines in web, tests.
Licence
The repository
LICENSE file checked at the pinned commit; the author agreed to inclusion.
The XERJ corpus
The author agreed by email on 2026-10-10. 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
cost-optimizationllmprompt-engineeringpythonragtoken-optimizationcontext-compressionllm-agents
Example questions
- How does llmslim implement cost-optimization?
- Where does llmslim handle “make v0.6.0 playground adaptive”?
- What does web do in llmslim?
Inside the indexed corpus
- Languages by size: Python 68%, TypeScript 28.2%, CSS 3.1%, Jupyter Notebook 0.5%, Shell 0.2%.
- On GitHub since 2026-06-15, last push 2026-10-31, 350 commits on main.
- The pin is 273 commits behind main; the corpus answers from the pinned code, not the newest.
Licence on GitHub and in the corpus
GitHub reported MIT for Thanatos9404/llmslim on 2026-10-31, and the LICENSE file at commit 333787d3fa was reviewed as MIT. They match, so answers from this corpus carry the same terms as the live repository.
Contributors
Yashvardhan Thanvi (@Thanatos9404) has 1 selected repository on the hub.
Using XERJ with llmslim
- RAG without a vector database: one hybrid index llmslim is tagged rag on GitHub.
- Search API or a vector database for agent memory?
- What is agentic memory? A plain answer llmslim is tagged agent-memory on GitHub.
- XERJ vs Mem0, Zep, Letta and Cognee for agent memory
The prompt
Paste it into your AI agent. It clones Thanatos9404/llmslim at the pinned commit and indexes it on your machine.
Search the GitHub repository Thanatos9404/llmslim with XERJ (https://hub.xerj.org/corpus/thanatos9404--llmslim). 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/Thanatos9404/llmslim llmslim && git -C llmslim checkout 333787d3faab96cc4480d12c2a02c1538f795c66 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./llmslim --url http://127.0.0.1:9200 --prefix llmslim --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
Yashvardhan ThanviAI, prompts and agents corporaxobotyi--cc-foundry-ai-helpers-prompt-engineeringprompt-engineering-guide12-factor-agentsmarcusaguiarmaciel-cmd/cato-plugindelphisecurity/xaidrbanzaicolo/sourced-intel
Stats: GitHub API, fetched 2026-10-31. Selected work and consent: the XERJ registry.