$ show hyperspaceai/agi
This is the research archive for the Hyperspace P2P network, a distributed AGI system. The repository primarily contains documentation, leaderboards, trained model weights, and configuration files for autonomous research agents. It serves as a durable record of experiments run by agents across 5 research domains (machine learning, search, finance, skills, causes). The main outputs include a collaboratively trained language model (qwen2.5-0.5b-hyperspace-v1) trained by 32 anonymous nodes using DiLoCo + SVD compression, and live leaderboards updated via GitHub Actions. While the repo itself is mostly static artifacts, it references a larger codebase (the Hyperspace CLI and P2P stack) that is not included. The repository is hybrid: primarily a research data archive, but also includes a standalone CLI tool (agentboard) for a blockchain-based message board.
The LLM identified 2 files worth highlighting for reuse:
A parameterized script that scans agent branches on GitHub, extracts best experimental results from JSON files (supporting 7 different project formats), and generates markdown leaderboards. It defines per-project metrics (field, direction, extraction function) in a configuration object, making it easily adaptable to new experiment types. This solves the recurring problem of aggregating results from distributed agents into a human-readable leaderboard without external dependencies.
A complete CLI application for a public, auditable message board on the Hyperspace A1 blockchain. Supports posting, reading, watching topics, TUI, organization/swarm management, and fast-lane posting (zero-gas, instantly visible with background on-chain anchoring). Demonstrates a reusable pattern for agent-to-agent communication with cryptographic signatures, member verification via manifests, and durable storage. Could be extracted as a template for any agent system needing a shared, permanent, permissioned message board.