Context compaction with decision models

RAM-efficient Rust coding-agent harness, listed as using Jev decisions for memory pruning, browser navigation and voice routing.

Open-source AI gateway for 100+ LLMs that can use Jev to classify requests for complexity routing and to compact tool results.

Claude Code plugin and npm library that replaces the compaction summary with Jev keep, truncate or drop scores for every tool call.

Calibrated context sieve for Claude Code: Jev judges each block of large tool output and hides confident-no blocks behind recallable stubs.

Codex hook that compacts large command and tool outputs, using Jev to rank which chunks matter and keeping the full output retrievable.

Recursive language model layer for coding agents that keeps inputs in a local evaluator, with optional Jev judge_many for typed calls.

Local proxy for Claude Code that uses Jev to remove stale tool results from the context once it reaches about 120K tokens, failing open.

Claude Code plugin sending small judgments to Jev: rule checks that block edits, verbatim compaction, subagent sizing and routing hints.

Retrieval layer for Codex that finds evidence locally, optionally ranks sanitized excerpts with Jev, and returns bounded, cited evidence.

Codex Decision: VS Code extension that trims repetitive lines from Codex tool output via Jev or OpenAI Decisions, linking the original.

Codex plugin that builds handoff packets by asking Jev whether each old read-only tool record should stay, keeping retained text verbatim.

Agent plugin that asks Jev whether the session is at a safe boundary to /compact and can trigger it on Pi and Claude Code.

Cursor CLI plugin that asks Jev keep-or-drop nouls for each tool call and result, then re-injects kept facts after compaction.

DeepSeek Harness plugin that asks Jev which tool results can be pruned early, delaying or avoiding lossy compaction.

DeepSeek Harness compaction backend that asks Jev which tool calls and outputs to keep, preserving everything else verbatim.

DeepSeek Harness jev_search tool that runs ripgrep, scores every hit line with Jev, and returns only the top rows above a cut.

DeepSeek Harness compaction plugin where Jev decides which tool results are still needed and code writes deterministic receipts.

DeepSeek Harness plugin where Jev prunes long tool output, screens fetched pages for injected instructions and gates completion claims.

Claude Code mod that picks reasoning effort per prompt with a Haiku judge, optionally Jev, and shows cache and context state.

Claude Code /fc command where Jev picks which old tool outputs to keep whole; the rest are trimmed and saved to files.

DeepSeek Harness port of fast-jev-compaction: Jev keep/truncate/drop verdicts per tool call replace lossy summaries.

Fork of fast-jev-compaction that calls Jev via OpenRouter with zero data retention enforced on every request.

Pi extension where Jev judges each completed tool call and result before compaction, keeping key evidence verbatim in the summary.

Local compaction proxy for Claude Code and Codex that compacts more often with local rules and keeps full history searchable.

Hermes Agent plugin that picks the model each turn with a direct TypeSafe Jev Choice and enforces trim-then-compress context handling.

Go-based Claude Code plugin where Jev reads code so the agent doesn't: semantic find, bounded questions and large-read takeovers.

MCP tool that asks Jev which files, web pages or snippets are relevant to a query, so the agent reads selectively.

Pipe grep or file lists into Jev to get every candidate scored, sorted and cut at a calibrated threshold, so agents read only what matters.

MCP server with record and recall tools: facts are logged during a session and Jev keeps only those relevant to the next task.

Claude Code plugin that picks model tier and effort per turn with Jev and weighs each switch against cost, with Jev-based compaction.