Title here
Summary here
Blog
Tabular Data in Fred: ReBAC-Scoped Parquet, S3, and DuckDB
Fred now treats tabular data like the rest of the corpus: document-scoped, team-aware, and authorization-first. This post explains why the old SQL-store model was limiting, how the new Parquet plus DuckDB runtime works, and what this changes for security, performance, and operations.
April 16, 2026 in SQL, architecture by Simon Cariou7 minutes
Rich Mode: Extending RAG with Direct Visual Evidence
An exploration of the structural limitations of text-based RAG systems, supported by benchmarks, and how Rich mode introduces a multimodal retrieval strategy that preserves and leverages images as first-class evidence.
April 13, 2026 in agents, architecture by Odelia Cohen6 minutes
Observability by Design in Fred: Prometheus, OpenSearch, and Spot
Fred now treats observability as a first-class platform capability. With Spot, users can discover Prometheus and OpenSearch tools over MCP, ask monitoring questions in natural language, generate exact PromQL, and persist audit reports to MinIO-backed storage.
April 3, 2026 in observability, platform by Simon Cariou9 minutes
Beyond Agent Framework Wars: Fred and the Infrastructure Layer
Fred does not compete in the agent framework wars; it focuses on the production infrastructure layer for governed agent execution.
February 21, 2026 by Dimitri Tombroff13 minutes
Document Ingestion Is Not a Side Effect
Document ingestion is a first-class architectural concern in agentic platforms, and fast attachment is not the same as durable corpus ingestion.
February 14, 2026 by Fred Team7 minutes
Durable AI Agents: Orchestrating the Future with Fred and Temporal
Fred extends its existing agentic backend with a Temporal-powered execution path for long-running tasks. Workflows remain resilient through retries, heartbeats, and durable state, while agent contracts and tool boundaries stay explicit and portable.
February 4, 2026 in architecture, ai by Dimitri Tombroff and Simon Cariou6 minutes
Relationship-Based Access Control in Fred with OpenFGA
Fred’s backend now ships a ReBAC model powered by OpenFGA. Tags, documents, and resource libraries inherit permissions, groups are first-class, and every check flows through centralized authorization—bringing Drive-like sharing semantics to agentic workflows.
December 18, 2025 in security, platform by Florian Muller and Simon Cariou7 minutes
Comparing Graph-Centric and Reflective RAG Agents in Fred
A comparison of Fred’s graph-centric RAG agent (Richard) and reflective RAG agent (Rico), including architecture and evaluation metrics.
December 16, 2025 in agents, architecture by Thomas Hedan5 minutes
Integrating External A2A Agents into Fred’s Backend
Fred now supports A2A agents alongside MCP agents. Developers can deploy standalone, language-agnostic agents and register them in Fred as first-class citizens. A new agentic bridge handles protocol translation, streaming adaptation, UI rendering, and security integration—unlocking industrial-grade agent development.
December 12, 2025 in platform, architecture by Nicolas Payneau, Dimitri Tombroff10 minutes
RAG That Pulls Its Weight: How Fred’s Retrieval Stack Leveled Up
Fred’s latest release strengthens retrieval: Lucene HNSW with cosine, semantic/hybrid/strict modes, corpus/global scope controls, chunk visibility, and attachment summaries injected into context. This post explains the why and the how.
December 11, 2025 in platform, update by Romain Perennes, Dimitri Tombroff and Simon Cariou5 minutes