This product was not featured by Product Hunt yet. It will not yet shown by default on their landing page.
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
EightD
Agent-native version control for parallel AI swarms
8d replaces Git for autonomous AI workflows. It drops file-locking for a lockless Merkle-DAG CRDT architecture, tracking parallel agent reasoning instead of just code diffs. Scale your multi-agent swarms without context loss or merge collisions.
Hey Product Hunt! 👋 I'm excited to introduce 8d — a cryptographically-sound, distributed state machine built exclusively for agentic AI workflows.
Why build another Version Control System? We realized that forcing AI workflows into Git is like putting a jet engine on a horse buggy. Git was designed in 2005 for human developers who make slow, sequential commits.
When you deploy modern multi-agent swarms (like dozens of coding or research agents working in parallel), Git physically breaks down with index.lock concurrency collisions. Worse, when agents reset branches, their reasoning—the cognitive "why" they did it—is lost forever, leading to massive token bloat and hallucination during merges.
How 8d fixes this: Instead of storing linear code diffs, 8d pioneers the CASM Architecture (Cognitive Agent State Machine). It models codebases as a non-linear cognitive memory graph.
🛠 Features: ⚡️ Lockless CRDT Set-Union: Parallel agents never block each other. 🧠 Cognitive Memory, Not Diffs: Tracks explicit agent reasoning loops and execution metadata. 🏎 Extreme Speed: Uses Rust NIFs for BLAKE3 hashing (10x faster than Git's SHA-1). 🕸 Native TCP Distro: Built on Elixir/Mnesia, bypassing the split-brain limits of distributed databases.
Stop letting Git throttle your AI swarms. We are entirely open-source, and I'd love to hear your feedback, answer questions about the math behind CASM, or hear about your craziest multi-agent scaling bottlenecks!
