Back to directory

Hussh Research

A consent-first research and product workspace for private AI agents, where individuals own their information through client-side encryption, scoped capability tokens and zero-knowledge memory storage.

Hussh Research

Hussh Research is the monorepo behind Hussh, a platform built around the idea that an agent should work for the person whose life it touches. Vault keys are derived and unlocked on the user's own device, so the backend only ever stores encrypted ciphertext and metadata and holds no unencrypted personal information or memory cards, and every operation requires a valid, scoped and revocable capability token rather than treating sign-in alone as consent.

The ecosystem centers on One, a primary relationship-layer agent that listens, remembers, decides and acts, which can summon specialist agents such as Kai for finance, Nav for privacy and consent management, and a KYC agent for identity verification. The monorepo includes a Next.js and Capacitor web, iOS and Android client and a FastAPI backend implementing the consent protocol and its agents.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.