HN Showcase
Back to browse
GitHub Repository

Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs

23 starsPython

Understand and reduce token usage with ContextSpy context profiler

by iezhy·Jun 15, 2026·6 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemSlick

Proxy-based token profiling for AI agents when LangSmith costs too much.

Strengths
  • •Wire-protocol interception means zero code changes to existing agents
  • •Visual dashboard breaks down tokens by category: system prompts, tools, files
  • •Tracks context evolution across sessions to spot cost creep
Weaknesses
  • •Certificate installation and proxy setup adds friction for new users
  • •Token optimization space getting crowded with LangSmith, Helicone alternatives
Target Audience

Developers using AI coding agents like Claude Code, Copilot, opencode

Similar To

LangSmith · Helicone · Braintrust

Similar Projects

Developer Tools●●●Banger

Ecotokens – Another token saver for CLI Agents

PreToolUse hooks filter shell output before it hits the model, saving tokens automatically.

Big BrainSolve My Problem
ansicode
102mo ago
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
103mo ago
Developer Tools●●●Banger

Engram adds universal context spine for AI coding IDEs

Heuristic DOM matching cuts LLM calls, saving 89% on tokens compared to naive context stuffing.

Big BrainSolve My Problem
NickCirv
101mo ago