Search

More Filters

Show More
Add Listing
Go Back

mycoder

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

MyCoder is a command-line interface and agent system for AI-powered coding tasks intended for developers. It provides a globally installable CLI named mycoder that can run prompts interactively, accept prompt files, and operate in fully automated sessions. The project supports multiple model providers including Anthropic Claude, OpenAI, and Ollama and includes an agent package for building and running sub-agents. It is extensible via a modular tool system, supports a Model Context Protocol (MCP) to access external resources, and offers GitHub integration to work with issues and PRs. Configuration is flexible and supports many file locations and formats. The repository also includes browser automation support via Playwright and features for parallel execution, message compaction, and hierarchical logging to aid complex coding workflows.

Links

Stars
531
App URL
https://github.com/drivecore/mycoder
Github Repository
https://github.com/drivecore/mycoder/blob/main/README.md

App Details

Features
The README highlights several concrete features. It supports multiple LLM providers and model configuration including provider, model, maxTokens, and temperature. The architecture is modular with an extensible tool system and an agent module that can spawn parallel sub-agents. It offers self-modification capabilities, hierarchical color-coded logging, and automatic message compaction to manage long context windows. GitHub integration and comment commands allow running agents from issue comments. Interactive corrections let a user send corrections to a running agent (Ctrl+M). Browser automation uses Playwright with system browser detection. Configuration supports many file names and formats with CLI arguments overriding files. The repo is split into packages for CLI, agent, and docs and includes development and release tooling.
Use Cases
MyCoder helps developers automate and accelerate coding tasks by generating, modifying, and testing code via natural language prompts and scripted workflows. It can run interactively or in unattended mode, accept corrections during execution, and be triggered from GitHub comments to operate on issues and PRs. The agent system can spawn sub-agents for concurrent task processing and uses project files and shell commands to construct context, reducing manual setup. Configurability and provider options let teams tailor behavior and models. Playwright integration enables browser-based sessions. Flags to disable prompts and upgrade checks make it suitable for CI and automated environments. The release and development tooling streamline packaging and contribution.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*