ai.arsentev/contextburnai

contextburn

Verified · 2 mo ago

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

Install

claude mcp add contextburn -- uvx contextburn

Our take

Measures coding-agent run efficiency by estimating how much paid token usage turns into output rather than repeated context reading. It is for developers and teams trying to understand or optimize agent cost and context behavior. A PyPI package is listed, which is a useful distribution signal, but zero stars suggest it is still early and should be validated against real workflows.

reviewed by hand · 2026-09-12

Something wrong or dead here? Report it

Verification record

last verified
2 mo ago
github stars
0
last commit
2 mo ago
archived
no
license
MIT
in registry since
2026-09-11

github.com/arsentev-ai/contextburn

More in ai

browse all →
reaai

REA

Verified · 10 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 10 days ago

claude-flowai

claude-flow

Verified · 39 days ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 39 days ago

tldrawai

tldraw

Verified · 40 days ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 40 days ago

codebase-memory-mcpai

Codebase Memory

Verified · 30 days ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 30 days ago

openmetadata-mcpai

OpenMetadata

Verified · 22 days ago

Official OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.

hand-reviewed15k starschecked 22 days ago

mobilerunai

mobilerun

Verified · 42 days ago

Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.

hand-reviewed9.4k starschecked 42 days ago