Cursor launching Origin 🔥
This space is heating up fast.
At Libra, we’re building the **AI Agent-native Version Control System** — not just another hosted git, but a complete rethinking that captures intent, reasoning, and exploration.
https://t.co/XpX6ejU675
We're launching code storage and git hosting.
Origin gives teams and agents a place to host, review, and collaborate on code.
Available this fall. Join the waitlist.
https://t.co/uamaIarJXY
Treat prompts as first-class deliverables.
Not random prompts or temporary instructions, but managed like code: version control, review, reuse and iteration.
👉https://t.co/KCtOK1jxqq
#ScalingSummitHK🚀 Excited to announce that Libra has been selected as one of the Top 8 AI Agent Demo Projects at Scaling Summit HK!
📷We'll be demoing our AI-native version control system,See you in Hong Kong!
Top 8 Selected AI Agent Demo Projects @ Scaling Summit HK 🇭🇰
Here’s what selected teams are building:
🔹Avinasi @BaraHealth_— Self-evolving health agent
A health agent designed to prevent decline through continuous optimization.
Tracks wearable data to generate personalized health goals and adaptive protocols.
🔹KOLECT @kolect_info — Social trading platform
A sentiment-powered quant platform where social signals become executable strategies.
Turning collective signals into real trading actions.
🔹DealAgent — From Chat to Commerce
An ERP-native AI agent enabling commerce workflows without traditional frontends.
Reimagining transactions through conversational interfaces.
🔹Awareness @AwarenessCloud — Memory layer for agents
A cloud-based memory infrastructure enabling long-term memory for AI agents.
Supporting multi-agent collaboration and persistent intelligence.
🔹CancerDAO @CancerDAOxyz — AI-driven cancer network
A patient-data-driven network for personalized cancer management.
Also building a community-driven data lake for biotech research.
🔹Syndicate — Multi-agent trading system
A crypto trading system leveraging debate, self-critique, and causal reasoning.
Moving beyond signal aggregation to structured decision-making.
🔹Libra @git_mono_AI — AI-native version control
A version control system linking prompts, reasoning, and code.
Enabling parallel workflows and multi-agent collaboration.
🔹MemExchange @youbetdao — Knowledge exchange for agents
A decentralized protocol for agents to discover, trade, and reuse knowledge.
Allowing agents to build on existing expertise.
These are not just demos.
These are early systems being built in real time.
👉 See them live in Hong Kong
https://t.co/62ixF1s9ei
A video shows how Libra automatically captures the reasoning process of an AI Agent, persists the reasoning trace, and manages it as versioned metadata. https://t.co/IepySwHXZr via @YouTube
Libra v0.4.0 is out now, and our new official website is live 🚀
Website: https://t.co/XpX6ejU675
Libra’s vision is to build a native version control tool for AI Agents.
📺How Libra manages reasoning processes as versioned information ->> https://t.co/IPQE5hsi5Q
Agents thrive when the repo is "legible" – structured docs, prompts, and invariants that agents can access in-context. But Git treats these as "just files," losing intent & provenance. Quote: "Context is a scarce resource... Too much guidance becomes non-guidance."
Just read OpenAI's eye-opening piece on "Harness Engineering" – they built a massive product with ZERO manual code, all via Codex agents generating 1M+ lines, 1,500 PRs, at 3.5 PRs/engineer/day. But traditional Git? It's buckling under agent-scale chaos.
https://t.co/0MKQu2G5ox
Big day! We're excited to announce our first public releases for the AI agent era:
Mega v0.1.0 • Libra v0.1.0 • ScorpioFS v0.1.1
Git-compatible monorepo stack in Rust: petabyte-scale + agent-native workflows.
Thread 👇
#AI#Agent#Monorepo#Rust#VCS
Mega + Libra + ScorpioFS = open pipeline for agents to clone, reason, edit & build at scale. MIT licensed. Rust-powered. Future-ready.
Star, try, contribute!
What will you build? 👇
#AI#Agent#VCS#Monorepo#Rust