Co-Pilot
Updated a month ago

labs

Hhashintel
0.0k
hashintel/labs
72
Agent Score

💡 Summary

This repository hosts experimental code snippets and applications for agent-based modeling and simulation tools.

🎯 Target Audience

Data scientists looking for simulation toolsDevelopers interested in agent-based modelingResearchers in AI and machine learningOpen-source contributorsStudents learning about simulation frameworks

🤖 AI Roast:Powerful, but the setup might scare off the impatient.

Security AnalysisMedium Risk

Risk: Medium. Review: shell/CLI command execution; outbound network access (SSRF, data egress); filesystem read/write scope and path traversal. Run with least privilege and audit before enabling in production.

github_star

Labs

A public laboratory for HASH's experiments 🧪

This repository contains code snippets, examples and experimental work made public. Projects from our private internal-labs (🔒) monorepo for experiments will be moved here and published when safe and practical to do so, in line with our commitment to open-source.

Apps

The apps directory contains the source-code and/or content for a number of runnable applications.

Simulation Tools

The HASH app seeks to enable its users to make better decisions by utilizing all of the information available to them. Generative simulation is a core part of realizing this vision. In anticipation of integrating these capabilities, we have developed a variety of standalone tools for agent-based modeling. These simulation tools remain experimental, but we are open to accepting contributions to these in line with our repository guidelines.

  • sim-core is an open-source, locally-runnable version of HASH Core
  • sim-core-plugins contains an example external plugin developed for hCore, which provides a visual interface for process modeling
  • sim-engine contains HASH Engine, a versatile agent-based simulation engine written in Rust (with support for TypeScript & Python sims)

Libs

Block Protocol Libraries

POCs

The pocs folder contains proof of concepts and other one-off experiments.

  • distributed_collab - Distributed Collab: a BEAM VM based system for publishing/subscribing to JSON Patches with core logic implemented in Rust
  • hash-agents - HASH Agents: an experimental setup for writing Python-based 'agents' that interface with LLMs
  • hash_helm_chart - HASH Helm Charts: An experimental Helm chart for deploying (now outdated, legacy) instances of HASH on Kubernetes

A number of older POCs can be found in our hasharchives organization, including:

5-Dim Analysis
Clarity7/10
Novelty8/10
Utility8/10
Completeness6/10
Maintainability7/10
Pros & Cons

Pros

  • Offers a variety of experimental tools
  • Encourages community contributions
  • Focus on agent-based modeling

Cons

  • Experimental tools may lack stability
  • Limited documentation for some components
  • Not all features are fully developed

Related Skills

pytorch

S
toolCode Lib
92/ 100

“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”

agno

S
toolCode Lib
90/ 100

“It promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.”

nuxt-skills

S
toolCo-Pilot
90/ 100

“It's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.”

Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.

Copyright belongs to the original author hashintel.