context-engine

Context Engine

Live demo: contextengine.sh

Context Engine is a toolkit for AI-enhanced deliberation, decision-making, and negotiation in large groups. It supports public and private questions and responses, AI-assisted input and analysis, permanent records, and cryptographic access control. It allows for no-code deployment of Soulbound Tokens for Groups. Designed for use cases such as public discourse, organizational decision-making, preference-related dataset creation, and turning stakeholder feedback into company-specific AI evaluations.

Architecture At A Glance

Context Engine separates how the web app is hosted from how each session establishes authority and stores data. EVM and Arweave are profile-specific options, not baseline dependencies. The current Hosted & Fast profile uses a per-session Cloudflare Worker and Cloudflare storage as its canonical backend, so it can run public or private sessions without an EVM transaction, RPC endpoint, gas, Arweave, or Lit. The Trustless & Slower profile deliberately opts into public EVM contracts and Arweave, with Lit required only when that encryption path is selected. The planned Company-Operated edition is intended to connect internal identity and key management, storage, networking, AI, and observability services, and can be entirely off-chain. For current profile requirements and publish behavior, see the session creation guide.

Deployment Modes

contextengine.sh is the hosted public web interface, and the static client can also be self-hosted. The former .xyz address redirects to this canonical site. App hosting, public/private session access, and the session infrastructure profile are separate choices. Participants never need deployer API keys.

Quick Start

Prerequisites

• Root scripts, worker bundling, contract tooling, and client workflows: Node.js 20.19+ or 22.12+ with npm 10
• Foundry (forge / anvil) for local-chain and root contract test workflows

Clone and Install

git clone https://github.com/AgalmicSoftware/context-engine.git
cd context-engine

nvm use 20
npm install
npm --prefix client install
npm --prefix client run dev

The React app runs on http://localhost:3000.

For testing, run modes, and deeper setup:

• docs/testing.md
• docs/run-modes.md
• docs/session-creation-guide.md
• docs/public-client-config.md#netlify-static-deploy for Netlify/custom-domain static frontend deploys

Features

Survey and Response Management

• Multiple question types: freeform, single- and multi-select, binary, rating scales, and quadratic allocation
• Optional encryption of responses and results
• Optional decentralized and permanent response storage in the public Arweave-backed profile
• Statistical / AI analysis and visualization of results
• Export results as .json, .csv, .pdf

Groups

• Cloudflare Groups for membership, invitations, and response filtering in Worker-backed sessions
• Optional no-code creation of Soulbound tokens (SBTs) for chain-backed groups
• Public minting, password-protected minting, time-limited minting, limited-number minting, and auto-claim URLs
• Role-based burn authorization (admin, minter, both, neither)
• Session and resource gating based on SBT ownership (encrypted titles, information, docURLs, tags)

AI-Assisted Tooling

• Voice-to-text input
• Question generation from file, URL, or text input
• Summaries and analysis of survey results and response clusters
• Optional interview research metadata for comparing AI draft predictions with reviewed submitted responses; see the interview research diagrams and schema notes
• Export deliberation snapshots and consensus statistics as evaluation / preference datasets for AI benchmarking and training
• OpenAI, Anthropic, OpenRouter, and custom provider paths

Agent and Telegram Access

• Optional Agent Bridge Worker with scoped /api/agent/* credentials and a machine-readable action catalog
• Optional Telegram bot and Mini App adapters over the same session boundaries
• Delegated membership, gate, storage, and chain authority rather than a second copy of canonical session state
• Setup and endpoint reference in workers/agentBridgeWorker/README.md

User and Deployer UX: Passkey Sign-On

• Users log in with a simple passkey / biometric flow (native PIN, fingerprint, or Face ID on phones)
• Login supplies a signing account for session identity; EVM-backed profiles can also use it as a chain account
• Hosted & Fast does not submit an EVM transaction, and its users do not need Ethereum, a wallet balance, or gas

Deployer UX: Sponsored Bundles

• Setup requirements follow the selected profile: the default Cloudflare profile needs a Cloudflare account/dashboard login and one AI-provider key; a Cloudflare API token is used only by Agent Session Wrapped or the explicit legacy deploy-helper fallback
• Sponsored bundles and advanced configuration can supply Arweave, EVM/RPC, Lit, or other credentials only when the selected decentralized or encrypted profile needs them; planned company-operated adapters will connect internal services instead

AI Discourse Corpus

The top-level ai-discourse-corpus/ directory contains reusable JSON sub-corpuses curated from AI policy, safety, governance, science fiction, practitioner interviews, evaluation work, debates, and enriched social-media discussion. Rights for that directory are described separately in ai-discourse-corpus/LICENSE.md: no ownership is claimed over upstream source material, and project-authored annotations are dedicated under CC0.

AI Opinions Benchmark

The top-level ai-discourse-bench/ package turns source-grounded question banks into repeated, polarity-reversed model runs and static Context Engine results reports. The client