AI/ML●●Solid
Entroly – Compress codebase context for LLMs by 78% using Rust
Entropy-based context compression beats naive token stuffing, but the category is crowded.
Big BrainNiche Gem
savetokens
102mo ago
Back to browse
GitHub Repository
8 starsTypeScript
Strata – 31-43% cheaper Claude Code reads via entropy, no parser
by noopz_·Mar 8, 2026·1 point·1 comment
AI Analysis
●●●BangerWizardryBig BrainShip It
Entropy-based code compression for Claude—no parser, works on any language, cuts context usage by a third.
Strengths
- •Works language-agnostic via structural boundaries, not language grammars—instant portability.
- •Hashline coordinates shrink edit references from ~70 chars to 7, compounding token savings across edits.
- •Similarity collapse handles repetitive code (60 class defs → 3 nodes), targeting real friction in agent coding.
Weaknesses
- •Requires Node 22+ and Claude Code integration—no standalone CLI or IDE support yet.
- •Unverified in production; no benchmarks on actual codebase-scale improvements or agent latency impact.
Category
Target Audience
Claude Code users working with large codebases; engineers optimizing LLM context usage
Similar To
Continue.dev context compression · Codeium indexing · Sourcegraph Cody syntax awareness
Similar Projects
Developer Tools●●Solid
Wet Claude – Go proxy that lets CC to profile and optimize its context
Reverse proxy lets Claude compress its own context before hitting the API.
Big BrainNiche Gem
buildoak
212mo ago
AI/ML●●Solid
Subagent-reuse, an MCP to reuse Claude Code subagent context
Merkle tree hashing detects stale files before reusing subagent context.
Big BrainSolve My Problem
h1r1ms
132mo ago
Developer Tools●●●Banger
Context Mode – 315 KB of MCP output becomes 5.4 KB in Claude Code
Context-aware summarizer cuts Playwright dumps from 56KB to under 1KB with zero friction.
Solve My ProblemSlick
mksglu
103mo ago
Developer Tools●●●Banger
TokenShield – cut your Claude Code bill 40-70%
Diff-based file reads and conversation deduplication slash token bills by 40%.
Big BrainSolve My ProblemShip It
curatedmcp
3316d ago
AI/ML●●Solid
Context Gateway – Compress agent context before it hits the LLM
SLM classifiers compress context based on tool call intent before LLM sees it.
Big BrainSolve My Problem
ivzak
97642mo ago