Answer-first summary67/100 GEO

Keen Code

Context-efficient CLI coding agent built in Go — minimalist terminal AI with turn memory and lazy-loaded skills.

developer-toolsStrong citabilityVisit site →

Your Citability Score

67/100
Completeness17/25
Citable structure25/25
Freshness25/25
Verified claim0/25
What to improve to rank higher
  • Completeness: Fill in description, category, URL, logo, tags, and audience.
  • Verified claim: Claim this project as its owner (and get verified) to earn full trust.

Promotion (Boost) does not change this score — it only changes ordering. This number reflects real, verifiable citability.

K

Keen Code

Invited

Context-efficient CLI coding agent built in Go — minimalist terminal AI with turn memory and lazy-loaded skills.

developer toolsCH-VER-676417 Mottakin ChowdhuryListed July 27, 2026
Visit Website
AI-Extractable Summary
What:Context-efficient CLI coding agent built in Go — minimalist terminal AI with turn memory and lazy-loaded skills.
For whom:Software engineers and developers who prefer terminal-native workflows and want a lightweight, context-efficient alternative to heavier coding agents
Key outcome:Ship code faster from the terminal with an AI agent that uses minimal context tokens — keeping costs low and responses focused
Category:developer tools
By:Mottakin Chowdhury

Structured for AI systems to extract and cite.

Citability Score

58/100
85
Identity
45
Evidence
15
Trust
50
Freshness
100
Classification
23
Impressions
0
Clicks
0
Saves
0
GQI Earned

Citable Outcome

Ship code faster from the terminal with an AI agent that uses minimal context tokens — keeping costs low and responses focused.

About

Keen Code is an open-source, terminal-based AI coding agent written in Go. It focuses on context efficiency through a "turn memory" system that discards raw tool traces after each turn, retaining only distilled summaries of files changed and failed commands. Unlike agents that load large MCP schemas upfront, Keen Code uses lazy-loaded markdown-based Skills, retrieving JSON schemas only at runtime. Ships with 6 core tools (read_file, write_file, edit_file, glob, grep, bash) and supports multiple LLM providers including Anthropic, Claude, OpenAI, Gemini, and DeepSeek.

Target Audience: Software engineers and developers who prefer terminal-native workflows and want a lightweight, context-efficient alternative to heavier coding agents.

What makes it different

  • Turn memory system discards raw traces — retains only distilled summaries for minimal token usage
  • Lazy-loaded markdown Skills instead of upfront MCP schema loading
  • Built entirely by AI agents under human orchestration — full development history preserved
  • Multi-provider support: Anthropic, OpenAI, Gemini, DeepSeek, Kimi and more

Tags & Classification

buildautomateopen-source
coding-agentterminal-aicontext-optimizationpair-programming
software-engineersdevelopersopen-source-contributors
developer-toolsai-mlopen-source
Platform: CLI Tool / Open SourceModel: Open Source

Links & Transparency

Website
github

Cite this Project

BibTeX
@misc{citablehub_keen-code,
  title = {Keen Code},
  url = {https://citablehub.com/p/keen-code},
  note = {Listed July 27, 2026. CitableHub ID: CH-VER-676417},
  year = {2026}
}
APA
Keen Code. (2026). CitableHub Software Index. https://citablehub.com/p/keen-code.
MLA
"Keen Code." CitableHub, 2026, https://citablehub.com/p/keen-code.