fast-jev-compaction vs token-optimizer
Claude Code plugin and npm library that replaces compaction summaries with Jev decisions: every tool call and result is scored, stale ones dropped or truncated, everything kept stays verbatim. — versus — Context-waste hunter for coding agents: hooks compress reads, bash and search output, checkpoint before compaction, and audit waste in configs, skills, MCP and memory — with a local dashboard.
Both fight context waste in Claude Code with hooks; token-optimizer compresses reads, bash and search output on the way in, fast-jev-compaction leaves everything verbatim and instead deletes whole tool calls a decision model judges stale.
| fast-jev-compaction | token-optimizer | |
|---|---|---|
| Stars | 4.2k | 2.3k |
| Forks | 221 | 178 |
| Language | TypeScript | Python |
| License | MIT | NOASSERTION |
| Last activity | 2 days ago | 3 days ago |
| Topics | coding, agents | coding, skills |
| Curated connections | 5 | 9 |
fast-jev-compaction — the curator's take
The sharpest idea in agent context management right now: never rewrite, only delete. A summary can silently lose the exact error, path or constraint you need twenty turns later; this scores each tool call and result with two noul questions against the whole conversation and then removes rather than paraphrases, so user and assistant text survives byte-for-byte. Fitting the state into 25k tokens is staged and documented, and it throws instead of guessing when history won't fit. Use it when losing a literal detail is the failure you fear. Don't use it if your bloat is prose rather than tool output - text is never shortened in the output - and note the honest limitation in its own README: a keep probability is not a proof that a result is safe to delete. Needs a hosted TypeSafe key on every compaction.
token-optimizer — the curator's take
The one token tool that argues with the others in its own README, and mostly wins the argument. Compressors like Headroom and RTK cover command output — roughly 15-25% of your context. Token Optimizer covers eight surfaces (bash, grep, tabular, file-re-read diffs, structure skeletons, archived large results, model verbosity, structural context) and then keeps going: checkpoints before auto-compact so savings survive it, model-routing nudges, loop detection, 30-day trend coaching, and per-component audits of CLAUDE.md, skills and MCP. It is cache-safe, injects nothing into your context, and measures before/after. The costs are real too: it is a large Python/TypeScript surface with 92 env knobs and 15 SQLite tables doing hook surgery on every Read and Bash, its headline dollar figures are counterfactual models against the author's own frozen baseline, and the license is non-standard. Pick RTK if you want one boring binary; pick this if you want the whole waste budget attacked and instrumented.