Back to directory

Easy-Coding-Agent

An autonomous terminal coding agent written in Python, with plan, code and chat modes, custom sub-agents, task tracking and evidence-gated memory that persists across long tasks.

Easy-Coding-Agent

Easy-Coding-Agent is a terminal coding agent built around an autonomous execution loop: it understands the codebase, plans the current phase, calls tools, edits files, runs shell commands, asks the user when it needs input, and keeps going until the task is verified or explicitly blocked. Its interactive command-line interface streams output and supports slash commands and a shortcut for switching between planning, implementation and chat-only modes.

A task manager tracks pending, in-progress, completed and skipped work as tool calls update the active list, and the agent detects loops such as repeated tool calls or repeated questions to avoid getting stuck. Custom specialist sub-agents can be created, listed, edited, previewed and invoked directly, and an evidence-gated memory system preserves references, tool logs, task state and source-backed claims across context loss on long-running tasks.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.