Developer Tools●●Solid
SigMap – 81.1% retrieval hit 5, 96.9% token reduce,zero deps
TF-IDF on signatures beats vector embeddings for file retrieval without the infra overhead.
Big BrainSolve My Problem
manoj079
1443mo ago
Back to browse
GitHub Repository
Token-efficient Markdown CLI for AI agents to navigate, search, and pack docs into bounded context windows
14 starsRust
Mdlens – Reduce token spend and boost retrieval on Markdown-heavy repos
by dreeseaw·Apr 26, 2026·3 points·0 comments
AI Analysis
●●SolidSolve My ProblemBig Brain
Scout command with bounded evidence packs beats naive file reads for token efficiency.
Strengths
- •Section-aware retrieval with IDs enables precise follow-up reads without full file loads
- •Built in Rust with JSON output for clean agent tool integration
- •Directly addresses token cost pain with hard max-tokens budgets per command
Weaknesses
- •Documentation retrieval is a solved category with established tools
- •Markdown-only scope limits applicability to codebase-heavy projects
Category
Target Audience
Developers building AI agents over documentation
Similar To
JinaAI Reader · Firecrawl · Context7
Similar Projects
Developer Tools●●●Banger
JSON to Md(gfm)
Cuts LLM token costs by 16% by stripping JSON punctuation before inference.
Big BrainZero to One
rajnandan1
407d ago
AI/ML●Mid
We cut >60% of tokens from agentic tasks by removing repeated context
Enterprise agent memory layer claiming 70% token savings over Zep and Mem0.
SlickBold Bet
longtermop
101mo ago
Developer Tools●●Solid
Ledger – Claude Code Token Spend Analyzer
Local SQLite ledger captures runaway Claude Code sessions before the bill shocks you.
Solve My ProblemCozy
tsv650
302mo ago
Finance●●●Banger
QuantumReckon – find your real cloud and AI spend, including tokens
First FinOps tool to quantify idle AI token spend alongside traditional cloud infrastructure costs.
SlickSolve My Problem
ssgonella
2016d ago
Developer Tools●●●Banger
SkillMesh (role-based tool routing for Claude/Codex)
Context routing cuts 73% of tokens while staying 9/10 accurate on role match.
Big BrainSolve My Problem
VarunReddy023
305mo ago