A
licenseA
qualityB
maintenanceNeuro-symbolic deterministic context pruning middleware. Reduces tokens by 60%, drops local CPU TTFT by 62%, and prevents IP leakage via formal SPARQL contracts.
2
3
MIT
ctxfw
Related Servers
Alternatives to ctxfw
No user-submitted related servers found.
Related Servers
- FlicenseAqualityAmaintenanceDeterministic repository context packing for AI coding agents: selects, compresses, and budgets only the files a task needs. Measured 83% fewer input tokens at the same task coverage, fully local, no LLM in the loop.99-
- AlicenseNot gradedqualityBmaintenanceReduces token consumption for AI coding agents by 50-70% through intelligent code context filtering, Git delta tracking, and local SQLite/Tree-sitter indexing.167 npmMIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to reduce token usage by condensing source code into AST skeletons, extracting specific symbols, compressing logs, and estimating token budgets.4MIT
- AlicenseAqualityCmaintenanceStructural memory for coding agents — 60% fewer tokens, refactor-safe, runs entirely on your machine.447 npm16Apache 2.0
- FlicenseNot gradedqualityBmaintenanceLocal-first code retrieval for AI agents — cuts codebase context from thousands of tokens to a few hundred, with zero hallucinated file paths.3-
TDQS
A4.4/5.0
Scored across 3 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: prune_file handles single-file interface extraction, resolve_context_bundle builds multi-module context, and evaluate_spec_axioms checks architectural specs. Cross-references in descriptions (e.g., 'use prune_file for isolated files') reinforce the boundaries, leaving no ambiguity.
Naming Consistency5/5
All three tool names follow the same verb_noun snake_case convention: prune_file, resolve_context_bundle, evaluate_spec_axioms. The verbs are specific and match the action, making the pattern predictable and easy to follow.
Tool Count5/5
Three tools is within the ideal 3-15 range and each earns its place. The server covers a focused workflow—file pruning, context resolution, and spec evaluation—without redundancy or bloat.
Completeness4/5
The tool surface covers the core pipeline (inspect single file, build context bundle, evaluate specs) with no obvious dead ends. Minor gaps exist like a dedicated tool for persisting or comparing context bundles, but agents can complete the core workflow without missing critical operations.
Maintenance
ActivityMaintained
ResponsivenessNo issues