HN Showcase
Back to browse
GitHub Repository

A global intent ledger and coordination protocol for autonomous AI agents. Agents check semantic market density and claim an idea before writing code - preventing duplicate effort. Shipped claims expose a resolution URL so other agents can discover and contribute instead of cloning. MCP + REST API.

1 starsPython

DejaShip – an intent ledger to stop AI agents from building duplicates

by mdn0·Mar 3, 2026·3 points·0 comments
Visit ProjectView on HN

AI Analysis

●●SolidBig BrainShip ItNiche Gem

Semantic deduplication for multi-agent systems, but corpus is tiny and false positives kill utility.

Strengths
  • •Genuine problem: agent swarms independently solving identical tasks wastes compute and resources.
  • •Clever framing: ledger + MCP protocol is architecturally sound for agent coordination.
  • •Zero friction: local embeddings (fastembed) + pgvector, no API keys or auth needed.
Weaknesses
  • •Corpus is too small to be reliable; author admits high false positive rate undermines trust.
  • •Chicken-and-egg: protocol only valuable if many agent operators adopt it, adoption unlikely without scale.
  • •No evidence of real-world test: is this solving a problem agents actually have, or a hypothetical?
Target Audience

Autonomous AI agent operators, teams running multi-agent systems

Similar To

Hugging Face Models Hub (project deduplication) · GitHub Trending (crowdedness signaling)

Post Description

When you give an AI agent a popular task like "build a micro-SaaS to make money," hundreds of agents are triggered to build the exact same things.

DejaShip is a semantic coordination layer to stop this wasted compute. Before writing code, the agent checks the "airspace". If a lot of similar projects already exist, the agent can pivot to a new idea, or if it is free in its choice, it can prefer to collaborate instead of blindly cloning it.

It works as an MCP server. Open source (MIT), no accounts or API keys required.

Under the hood: The backend embeds keywords locally using fastembed to search pgvector for semantic collisions.

To be transparent: The MVP is new, so the data corpus is tiny today. The value of this protocol only grows as more agent operators plug it in - or help decide how this coordination can be improved. (One of the biggest issues right now is the amount of false positives; it definitely needs improvement).

Site links and MCP installation instructions are on the GitHub README. (npmjs package: dejaship-mcp).

I'd love your brutal feedback.

Similar Projects

Developer Tools●Mid

Taking a shart at the first programming language designed for AI agents

The README actually lays down concrete design choices: four cell types (Transformer, Reactor, Keeper, Channel), a Universal Contract with Intent Ledgers, and Merkle-based signatures plus a constitutional validator. Interesting on paper, but the repo looks embryonic — the quickstart is truncated, there are no releases or demos, and the bold architectural claims outpace the visible implementation.

Bold BetRabbit Hole
haltcatchwater
203mo ago