Safe agent infrastructure
Collection
Runnable building blocks for agents you can trust: git-native coordination, policy-mediated data access. • 1 item • Updated
AI & ML interests
Applied AI. Agent infrastructure, local inference, and policy gates you can actually run.
Recent Activity
dipankarsarkar
updated a
collection about 2 hours ago
dipankarsarkar
updated a
collection about 11 hours ago
dipankarsarkar
updated a
collection about 14 hours ago
dipankarsarkar
published a
dataset about 14 hours ago
dipankarsarkar
updated a
dataset about 14 hours ago
dipankarsarkar
updated a
collection 1 day ago
dipankarsarkar
updated a
Space 1 day ago
dipankarsarkar
published a
Space 1 day ago
dipankarsarkar
posted an update 1 day ago
Post
58
Your issue tracker is in the wrong place.
It lives on a server. Your code lives in git. So every time an agent picks up work it makes an API call, burns a token, fights a rate limit, and still cannot see what the other agent just did.
Move the issues into the repo. Append-only event log in git refs. Branches when you branch, merges when you merge, CRDT so two agents never conflict. No server, no database.
The coordination signal that PR-level telemetry misses lives before the pull request. The paper, and a live demo running the real tool:
Before the Pull Request: Mining Multi-Agent Coordination (2606.19616)
https://huggingface.co/spaces/neullabs/grite
If your agents share a repo, where does their shared state actually live right now?
It lives on a server. Your code lives in git. So every time an agent picks up work it makes an API call, burns a token, fights a rate limit, and still cannot see what the other agent just did.
Move the issues into the repo. Append-only event log in git refs. Branches when you branch, merges when you merge, CRDT so two agents never conflict. No server, no database.
The coordination signal that PR-level telemetry misses lives before the pull request. The paper, and a live demo running the real tool:
Before the Pull Request: Mining Multi-Agent Coordination (2606.19616)
https://huggingface.co/spaces/neullabs/grite
If your agents share a repo, where does their shared state actually live right now?
dipankarsarkar
authored 10
papers 2 days ago
The Correctness Illusion in LLM-Generated GPU Kernels
Paper • 2606.20128 • Published
Before the Pull Request: Mining Multi-Agent Coordination
Paper • 2606.19616 • Published
Epistral Network: Revolutionizing Media Curation and Consumption through Decentralization
Paper • 2402.04881 • Published
Navigating the Knowledge Sea: Planet-scale answer retrieval using LLMs
Paper • 2402.05318 • Published
FairFlow Protocol: Equitable Maximal Extractable Value (MEV) mitigation in Ethereum
Paper • 2312.12654 • Published
Decentralized Deepfake Detection Blockchain Network using Dynamic Algorithm management
Paper • 2311.18545 • Published
Centralized Intermediation in a Decentralized Web3 Economy: Value Accrual and Extraction
Paper • 2311.08234 • Published
Towards Universal Atomic Composability: A Formal Model for Multi-Rollup Environments on Ethereum
Paper • 2311.00422 • Published
Generalised DePIN Protocol: A Framework for Decentralized Physical Infrastructure Networks
Paper • 2311.00551 • Published
Curriculum generation using Autoencoder based continuous optimization
Paper • 2106.08569 • Published