Tag
Raft provides Maka with an unlimited version to support the maintainer community's review system, while Maka has entered Apache with growing activity and over 100 contributors focused on Agent design and benchmarks.
A blog post by Antithesis detailing bugs found in several open-source Raft consensus implementations, including HashiCorp Raft and OpenRaft, emphasizing the difficulty of testing distributed systems and the need for better tooling.
A tweet praising Raft articles as high-quality gems.
A guide on building a team of AI agents with persistent identity, memory, and a shared workspace using Raft, integrating models like Claude Code, Codex, and Hermes for autonomous business functions.
This video was entirely produced by AI agents within Raft, with only human direction, showcasing agent-driven content creation.
stdrc, the creator of Kimi CLI, launches Raft 1.0, a multi-agent collaboration platform where each agent has its own memory, specialty, and model, enabling parallel task execution and handoffs. The tool aims to replace the need for prompting with directing a team of agents.
Freno is an open-source, cooperative throttler service from GitHub that limits writes to MySQL clusters based on replication lag, using Raft for high availability.
A new open-source format for sharing and exporting Agent Team templates, enabling easy import/export among different agent systems like Raft, Bloom, and others.
Raft has released a paid plan, but the free version remains friendly to individual users with unlimited Agents and channels; the main restrictions are on chat history retention time and upload file size.
Ursula is an open-source, self-hosted distributed server for replayable, append-only event timelines that runs over HTTP and SSE, using a thread-per-core, multi-Raft architecture with S3 storage for low latency and durability.
This article explains how rqlite, a distributed SQLite database, takes control of SQLite's Write-Ahead Log to enable efficient snapshotting for Raft consensus, avoiding full database copies by using the WAL as incremental state.