Radar / AI infrastructure / Kernl (dspm-memory)
Kernl (dspm-memory): training-free LLM memory compression via semantic patches
A MIT-licensed Python package (pip install dspm-memory) that compresses multi-turn LLM conversation memory by ~80%+ by converting turns into typed semantic patches (constraint, decision, code, entity) with structural protection for critical patches; backed by a Zenodo preprint.
Why it matters
Unlike naive truncation, it structurally guarantees critical constraints survive under fixed token budgets — the exact failure mode that breaks long-running coding agents — and it's shipping as installable software today, not just a paper.
What you could build with it
A startup shipping a long-running coding assistant could plug dspm-memory into its chat pipeline to hold full-day sessions inside a fixed token budget, keeping every hard constraint from early turns intact while cutting inference cost.
Does it hold up?
Too early to judge — PyPI 0.1.8 shipped 2026-10-05 and the repo has 7 stars; the 100%-retention claims rest on the author's own benchmarks, and the Zenodo preprint gives the method for independent checks but no third-party reproduction exists yet.
Learn more
First spotted on github: source.
More AI infrastructure
Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Context Mode: context-window optimization for AI coding agentsMCP server for AI coding agents that sandboxes verbose tool output and persists session memory, cutting context use by…infra · JEV 0.74StrataOpen-source inference engine that runs the 125B-parameter Qwen3.8-Flash-Next MoE on a single consumer GPU with 12GB+…infra · JEV 0.74Microsoft releases 301,000 Copilot coding-agent tracesMicrosoft open-sourced 301,026 GitHub Copilot coding-agent sessions (9.3M model calls, 8.7M tool calls) with timings…infra · JEV 0.71claude-memCaptures tool-use observations across agent sessions, compresses them with AI into SQLite + Chroma hybrid search, and…infra · JEV 0.7
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.