overstory and praktor

These tools are competitors, as both provide multi-agent orchestration for AI coding agents, specifically mentioning Claude Code, with Overstory offering a broader set of pluggable runtime adapters and Praktor focusing on Telegram I/O, Docker isolation, and swarm patterns with a UI.

overstory
70
Verified
praktor
41
Emerging
Maintenance 25/25
Adoption 10/25
Maturity 11/25
Community 24/25
Maintenance 13/25
Adoption 5/25
Maturity 9/25
Community 14/25
Stars: 979
Forks: 183
Downloads:
Commits (30d): 329
Language: TypeScript
License: MIT
Stars: 11
Forks: 3
Downloads:
Commits (30d): 0
Language: Go
License: MIT
No Package No Dependents
No Package No Dependents

About overstory

jayminwest/overstory

Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more

Spawns isolated worker agents in git worktrees coordinated via SQLite-backed messaging, merging results through tiered conflict resolution. Supports 11+ pluggable runtimes (Claude Code, Pi, Gemini, Aider, Goose, Amp, etc.) via a unified `AgentRuntime` interface. Includes live TUI dashboards, per-agent inspection, token cost tracking, and explicit warnings about compounding error rates and debugging complexity in multi-agent swarms.

About praktor

mtzanidakis/praktor

Multi-agent Claude Code orchestrator with Telegram I/O, Docker isolation, swarm patterns, and Mission Control UI

Implements a Go gateway that routes Telegram messages to named Claude agents via AI-powered classification or explicit `@agent_name` prefixes, with per-agent SQLite memory databases using hybrid FTS5+vector search for persistent recall across sessions. Each agent runs in isolated Docker containers with hot-reloadable YAML configuration, AES-256-GCM encrypted secrets management, and optional integrations including web/browser automation, voice transcription (Whisper), email routing (AgentMail), and on-demand package installation via Nix. Supports graph-based multi-agent swarms, scheduled cron/interval tasks with parallel execution, and real-time WebSocket updates to a Mission Control dashboard.

Scores updated daily from GitHub, PyPI, and npm data. How scores work