Show HN: PeopleMesh, Semantic Search for People
PeopleMesh is an AI-powered semantic search platform designed to help organizations improve internal discovery and collaboration. It enables users to find colleagues, projects, communities, and opportunities using natural language queries, leveraging embeddings and metadata for relevant results. Built with privacy and security in mind, it supports GDPR compliance and offers open-source core software with enterprise extensions.
- ▪PeopleMesh uses semantic search and vector embeddings to match users with relevant colleagues, projects, and internal opportunities.
- ▪The platform is privacy-first, featuring granular consent controls, pseudonymized audit trails, and GDPR-aligned data rights workflows.
- ▪It operates as a graph-like mesh of organizational nodes and supports integration via web app, API, and MCP for AI assistants like ChatGPT and Claude.
- ▪PeopleMesh is open-source under Apache 2.0, with enterprise plugins available separately for systems like Slack, LinkedIn, and Workday.
- ▪The platform can be run locally using Docker, Java, and Maven, with development support for Ollama and OpenAI backends.
Opening excerpt (first ~120 words) tap to expand
PeopleMesh The right match in your mesh. PeopleMesh is the AI-powered matching layer for modern organizations. It helps people discover the right colleagues, internal opportunities, communities, and projects through semantic search that understands context, not just keywords. By combining embeddings with metadata-based ranking, PeopleMesh surfaces high-signal matches faster, cuts through noise, and improves internal mobility and collaboration. Built privacy-first, PeopleMesh includes granular consent controls, configurable retention, and GDPR-aligned data rights workflows. Available via web app, API, and MCP integrations for AI assistants. Open-source at the core. Enterprise-ready in practice. Never built on personal data monetization.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.