A
licenseA
qualityA
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.941 PyPI9-
- 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
- AlicenseAqualityAmaintenanceEnterprise AST codebase context reduction engine with up to 95% token savings, 20 tools, polyglot support, and zero-leak security guardrails.15369 PyPI9MIT
- 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.426 npm17Apache 2.0
TDQS
A4.5/5.0
Scored across 5 tools
Disambiguation5/5
Each tool targets a clearly distinct purpose with explicit cross-references: prune_file for single-file contracts vs. resolve_context_bundle for multi-module graphs, evaluate_spec_axioms for specs vs. evaluate_patch for diffs, and query_audit_ledger for read-only forensic retrieval. No overlapping responsibilities remain ambiguous.
Naming Consistency5/5
All tool names use snake_case with a verb-first pattern (prune_file, resolve_context_bundle, evaluate_spec_axioms, evaluate_patch, query_audit_ledger). The convention is consistent throughout with no mixed styles or vague verbs.
Tool Count5/5
Five tools provide a well-scoped set covering context pruning, dependency resolution, two evaluation phases, and audit querying. Each tool earns its place without redundancy or obvious missing operations.
Completeness4/5
The surface covers the core workflow: context extraction, bundle building, spec evaluation, patch evaluation, and audit ledger querying. Minor gaps exist around explicit session/breaker management or audit initialization, but agents can work around these.
Maintenance
ActivityActive
ResponsivenessNo issues