Release v0.11.0
The context layer for production AI agents: local-first context planning, compression and runtime for LLM apps.
Status: Beta
Brought to you by:
yashvt
Originally created by: Thanatos9404
Release prep for llmslim 0.11.0, approved in chat for the launch. After merge, I tag v0.11.0 on main, publish the GitHub release (release.yml uploads to PyPI), verify a clean install, republish server.json to the MCP Registry, and move the website and Studio to 0.11.0.
llmslim wrap claude / llmslim proxy (#67): cache-safe and thinking-safe tool-output compression for Claude Code.LLMSlimToolOutputMiddleware for LangChain 1.x agents (#68).PostgresStore (#66): several processes or machines can share one memory.llmslim 0.1.0 (#72).uv build produces llmslim-0.11.0 (wheel and sdist), and twine check passes.112 -> 72 tokens (35.7% fewer), unchanged;proxy, mcp and postgres extras, llmslim wrap --help and llmslim proxy stats work;gh issue list --json output goes through the JSON path (7,442 -> 2,288 tokens);PostgresStore imports.
Originally posted by: vercel[bot]
The latest updates on your projects. Learn more about Vercel for GitHub.
Ticket changed by: Thanatos9404