EVOKE
OS-like memory management for the LLM KV cache.
14 projects, grouped by kind. Each entry links to a detail page with the full write-up, stack, and source.
Public repositories, MIT or Apache licensed.
OS-like memory management for the LLM KV cache.
Reactive LLM inference. When you edit an LLM's context, redraft reuses the stale answer as a self-speculative draft, so decoding cost tracks how much of the answer the edit changed. Implemented as a streaming mode inside llama.cpp.
Incremental computation engine for Rust. Tracks dependencies between computations automatically and only reruns what's actually affected.
A universal memory layer for AI coding agents. Ingests conversation history from Claude Code, Cursor, and other tools into a single SQLite-backed store with vector and full-text search, then serves it via MCP so any AI agent can recall what you've discussed, decided, and built across projects and machines.
Content-addressed cache for AI agent loops. Returns exact bytes from prior executions instead of re-running tools or re-calling LLMs.
Put your wardrobe in rows. Snap. Organize. Wear.
Consolidating what a model learns about its user (preferences, habits, how they want things done) into LoRA adapter weights, so the model carries them itself. First public result: Unwritten Rules, a real personal rules file trained into a rank-16 adapter on Qwen3.5-9B.
A month of research on open Jev-style decision models: a decision router for my agent harness, three small public models, and Kev on llama.cpp.
A standard for AI-generated code to carry machine-checkable certificates of correctness, plus a Python reference implementation and a finetuned model that generates them.
Automated testing for LLM skills. Launches Claude Code or Cursor as subprocesses, runs scenarios in isolated workspaces, and reports what passed and what didn't.
Closed-source products and client work.
The hosted version of wardrowbe. Virtual try-on, iOS and Android apps, cloud sync, fashion subscription.
Generative-AI image SaaS. 2,000+ users, 7,000+ images transformed. AI headshots, glamour shots, conceptual art.
Smaller builds and experiments.
Older work from 2018–2020 is in the archive. Interactive explainers live at learn.anyesh.me ↗.