Context compaction with decision models

npm CLI that screens large agent tool outputs with Jev, returning compact typed decisions and IDs while originals stay recoverable.

Dependency-free TypeScript library that converts raw app and game state into labelled bands and pruned lists that Jev reads reliably.

Vercel AI SDK layer that uses Jev to auto-approve, ask a human or block each tool call, and to prune irrelevant tools before a turn.

Claude Code, Codex and pi plugin that hands non-writing agent steps to Jev and escalates writing or unsure steps to the LLM.

Self-hosted Go gateway for LLMs and decision models that prunes context, and audits and calibrates Jev or open-rlcd decisions.

Pi-based coding agent where a small judge (Jev by default) answers yes/no, choice and score questions at 38 decision points per turn.

MCP gateway that trims noisy tool output and offers task classification and review advice, splitting work between local Laya and Jev.

Design-phase proposals for verbatim, Jev-guided context compaction in Kimi Code CLI via a forked mutating PreCompact hook.

Zero-build local playground for Jev with browser-agent, intent routing and context-pruning presets, including a Playwright agent.

Agent context compactor where Jev scores transcript segments to keep verbatim or move behind a recoverable pointer.

Jev-style skill router for OmO: frozen Qwen2.5-0.5B plus a small head scores the skill catalog and trims the system prompt to top-K.

Pi extension that dedupes repeated file reads and, opt-in, has Jev mark passing-test noise in long logs, with verbatim recall.

JIT-JEV Context OS: deterministic context compiler plus a Jev System 1 gate that scores AST relevance, test proofs and tool targets.

Post on X arguing that agent context compaction should be a Jev keep-or-drop decision rather than a summarisation prompt.

X post by Theo arguing that decision-model context compaction is reconstruction, not filtering, and is a poor strategy.