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
Fast local-first Rust CLI for codebase metrics, AST-compressed LLM context bundles, and built-in MCP server.
78 starsRust
Sephera – AST-compressed context packs and native MCP server in Rust
by reimisdev·Apr 3, 2026·2 points·0 comments
AI Analysis
●●SolidBig BrainNiche Gem
Tree-sitter AST compression cuts LLM context tokens 50-70% while preserving API structure.
Strengths
- •AST compression extracts signatures while replacing bodies with placeholders
- •Built-in MCP server integrates directly with Claude Desktop and Cursor
- •Deterministic context bundles with .sephera.toml for team configuration
Weaknesses
- •Pre-1.0 release with limited language support beyond Rust and Python
- •Codebase Q&A space already crowded with Cursor, Continue, and Cody
Category
Target Audience
Developers building AI-assisted code workflows
Similar To
Cursor · Continue · Sourcegraph Cody
Similar Projects
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
Developer Tools●●●Banger
Tokf – Stop wasting LLM context on verbose build output
Cuts cargo test output from 61 lines to 1 — saves 60-90% of wasted LLM tokens.
Big BrainSolve My ProblemDark Horse
risethagain
102mo 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
Codemode-x – Compress any API into 2 MCP tools for Claude Code
Two MCP tools replace hundreds when typical integrations need one tool per endpoint.
Big BrainWizardry
codelitt
112mo ago
Infrastructure●●Solid
See – searchable JSON compression (offline 10-min demo)
Schema-aware JSON compression stays searchable; reaches 7.7% vs Zstd's 13.7%.
Big BrainWizardry
Tetsuro
503mo ago