Cosolvent

The open-source headless marketplace engine for thin market formation. A full sponsor admin dashboard, plus a powerful API for building a custom participant frontend using AI.

View Feature Sheet ↓ Explore Repository →

Build Without Boundaries

As part of the MarketForge ensemble, Cosolvent serves as the open-source layer. It provides the essential digital infrastructure that connects isolated buyers and sellers within highly specialized, low-volume ecosystems.

Rather than spending months building role permissions, deal-flow assembly, and semantic scaffolding from scratch, Cosolvent allows you to generate a functional marketplace structure instantly, ready to be customized for your exact vertical.

Core Features

  • Matching Engine: Pre-built logic for resolving complex semantic matches.
  • Deal Assembly: Manage the multi-step lifecycle of thin market deal negotiations.
  • Role Permissions: Native support for multi-party structures, including facilitators and intermediaries.
  • Open Source: MIT License ensures you own and control what you build.

The Content Match Story — Knowing Before Committing

Most matching platforms announce a match. Cosolvent argues for one.

When two parties are matched, Cosolvent generates a Content Match Story — an AI-authored narrative that explains why the pairing is promising and what they could plausibly accomplish together. Not a profile summary. Not a referral. A case, made on behalf of the match.

Delivery is progressive and privacy-respecting: the story begins anonymously, so both parties can assess fit before any identifying information is exchanged. Identity is revealed only on double opt-in. This means participants arrive at their first conversation already understanding the match argument — wasted calls drop, conversion on genuine matches rises, and every interaction starts with shared context rather than mutual assessment from scratch.

In thin markets — where each viable match is rare and every trust withdrawal is costly — the Content Match Story is not a convenience feature. It is a structural intervention that makes low-density markets viable.

Scope Boundaries: What We Build vs. What You Build

Cosolvent is deliberately architected as a headless marketplace engine. It provides the universal infrastructure for thin market formation, but explicitly defers the participant-facing interface to the market sponsor.

  • Frontend UIs: Cosolvent provides APIs. The vertical sponsor builds the web or mobile app.
  • Monetization & Payments: We defer payment processing and business models to existing tools like Stripe.
  • Trust & Verification: Escrow, dispute resolution, and regulatory compliance are handled by the sponsor.
  • Digital Twins: Simulated populations belong in ClientSynth, separated from live market data.
View Feature Sheet ↓ ⬇ Roadmap (PDF) Explore Repository → ← Back to Ecosystem

Cosolvent Feature Overview

✅ Implemented    🔜 Planned

Configuration & Deployment
YAML-Driven Marketplace DefinitionDefine participant types, schemas, permissions, and discovery settings in a single marketplace.yaml file.
Deterministic Compiler PipelineYAML → normalize → hash → render → write → manifest. Reproducible artifact generation with drift detection.
Browser-Based Setup PanelVisual configuration UI with presets, real-time validation, and live YAML preview.
Docker Compose DeploymentSingle-command launch: API server, PostgreSQL + pgvector, Redis, ARQ background workers.
🔜AI-Assisted ConfigurationAI assistant generates config suggestions from conversational market description.
🔜Multi-TenancyTenant isolation for hosting multiple marketplaces on a single deployment.
Profile Infrastructure
Dynamic Profile SchemasRuntime Pydantic models generated from config. No hard-coded entity types.
Three-Tier Field VisibilityEvery field tagged public, protected, or private with enforcement at the API layer.
Configurable OnboardingPer-type onboarding: manual/auto approval, document uploads, AI extraction, completeness thresholds.
🔜Gallery / Matching SeparationSplit into a curated gallery layer (browsing) and a richer matching layer (AI-only signals).
🔜Group / Cooperative TypeGroups of small producers participate as a single entity with aggregated profiles.
AI & Semantic Search
AI Document ExtractionLLM reads uploaded documents and extracts structured profile fields automatically.
Semantic Vector Searchpgvector cosine-distance search with metadata filtering and configurable thresholds.
Hybrid & RAG SearchTwo retrieval modes — hybrid (vector + keyword) and rag_strict (vector-only with grounding).
Multi-Provider AIProvider-agnostic LLM layer supporting OpenAI, OpenRouter, and Google Gemini.
🔜Knowledge Slot IntegrationSponsor-curated domain knowledge library with vertical-specific metadata and domain Q&A.
🔜VLM IntegrationImage-based document extraction for certificates, invoices, and product photos.
Matching & Deal Engine
Participant DiscoveryConfig-driven search with filter fields, anonymous/authenticated results, and similarity thresholds.
🔜Bidirectional MatchingMutual preference matching considering both parties' profiles.
🔜Deal Data ModelStructured deals linking principals, facilitators, role slots, product, route, and timeline.
🔜Handoff ArtifactPlatform's primary deliverable — assembled from profiles, signals, conversations, and recommendations.
🔜Anticipatory MatchingProactive notifications when new listings match a participant's needs.
Communication
Conversation LifecycleCreate, accept, reject, and close conversations with full state tracking.
Real-Time WebSocketLive message delivery via WebSocket connections.
Config-Driven RulesConversation initiation rules defined per participant-type pair in marketplace config.
🔜Progressive Trust GatingCommunication channels unlock progressively as trust stages advance.
Trust & Verification
Admin Approval WorkflowBinary trust gate — admin manually approves or rejects participant applications.
🔜Verification PipelineAuto-analyze documents for consistency and assign verification confidence scores.
🔜Reputation SystemTrack transaction outcomes, response times, and dispute rates.
🔜Progressive Trust StagesSix-stage trust ladder from anonymous browsing to post-transaction evaluation.
Admin & Developer Tools
Admin DashboardAggregate marketplace statistics, user management, and application approval.
OpenAPI DocumentationAuto-generated interactive API docs at /docs.
Drift Detectioncompile --check verifies generated artifacts match current config.
36+ Unit TestsCoverage across config, compiler, permissions, visibility, schemas, and more.
Background Job ProcessingARQ worker pool for async document processing, embedding generation.
Architecture
LanguagePython 3.11+
API FrameworkFastAPI
DatabasePostgreSQL + pgvector
Cache / QueueRedis + ARQ
AI ProvidersOpenAI · OpenRouter · Google Gemini
LicenseOpen Source (MIT)