Keen Code is a context-aware terminal-based coding agent written in Go. It supports multiple providers, MCP servers, subagents and agent skills, and adds controllable tool output retention, hashline edits, compaction, a permission system, session management, multi-agent orchestration and a task classifier that routes work using decision models.
Be the first to rate Keen Code. Your feedback helps other users decide.
Several AI providers sit behind the same CLI.
Tool output retention is configurable and compaction trims long sessions.
A decision-model classifier decides how a request is handled, with documented fail-open behaviour.
Similar tools in the same category — compare side-by-side
TenseMem is embedded, deterministic state memory for AI agents, described as memory that knows its t...
Inillucent is an embedded SQL database written in Rust and built as an agentic database. It implemen...
Lumabri runs a private inference service across your own computers and servers, powered by Colibri a...
Guides and comparisons about code tools
Eight new tools that decide where a coding agent runs, how many run at once, and how you keep working in the same file it is editing.
Ten Show HN projects for running several agents at once: orchestrators, subagents in isolated worktrees, shared memory trees and browser relays.
Eight Show HN projects that handle the unglamorous layer: consumer-GPU serving, remote tensors, vector-ready storage, semantic layers and agent payments.
Which AI coding assistant actually saves you time? GitHub Copilot vs Cursor vs Codium in 2026, with real comparison and recommendations by use case.
How to choose an AI coding tool in 2026: inline completion, repo chat, and local privacy, compared across Copilot, Cursor, Codeium, and more.
