Prokop

Prokop is an open-source coding workspace where AI agents keep memory and skills across projects.

Prokop is an open-source coding workspace where AI agents keep their own memory and skills, search earlier sessions, and learn from finished work. It lets users work with the same coworker instead of briefing a stranger every session. The platform runs on the user's machine using Claude Code, Codex, or Prokop's own runtime. Memory and skills are stored as plain Markdown files on disk, and learning edits these files rather than model weights. The workspace includes features for parallel work in Git worktrees, mid-turn messaging, self-explanatory approvals, and mobile access.

Prokop at a glance

Best for: Software engineer
Runs on: macOS, Linux, Web, iOS, Android, self-hosted, open source
Pricing: Free and open source under the Apache 2.0 license.
Released: October 2026
Category: AI coding tool
Website: github.com/prokopai/prokop

Key features

Retain memory and skills per agent and project
Search earlier sessions for past decisions
Run multiple sessions side by side in Git worktrees
Use Claude Code, Codex, or Prokop runtimes
Send messages to agents mid-turn
Review self-explanatory command approvals
Edit Markdown memory files on disk

Use it for

Develop code with persistent AI agents
Run parallel coding sessions side by side
Review and commit changes within the session
Access coding sessions from mobile devices

Companions

Tools that articles about Prokop recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to Prokop

Pro Workflow — It creates persistent, searchable memory and wikis for coding agents.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
pstack — Improves AI coding agent outcomes with rigorous workflows.
Traycer — Keeps AI agents aligned with structured specs and task lists.
AI Memory — Shared memory for coding agents that works across machines and team members.
Kolo — Teams share one browser session to watch, type, and control AI agents together.
OpenViking — Unifies agent memory, knowledge RAG, and skills into a single directory structure.
Genkit — Provides unified APIs and local developer tools for AI application workflows.
CopilotKit — Connects your application to AI agents with generative UI and human approvals.
arcKode — Runs fully locally via Ollama with symbol-level code indexing for compact VRAM setups.
Alook — Connects existing local coding agents to team communication channels.
claude-mem — It shares persistent, searchable agent memory across sessions and devices.

All Prokop alternatives