Back to directory

gald3r

A file-based shared memory for AI coding tools that keeps tasks, bugs, plans and constraints synchronized across different agents and editors, so planning in one tool and coding in another loses nothing.

gald3r

gald3r drops a persistent, file-based store into a repository that every connected AI coding tool reads and writes, so a task planned in one tool can be picked up and implemented in another without re-explaining context. Its software-delivery workflow can run multiple compatible agent swarms against one coordinated project board, retain accepted reviews across an interrupted integration, escalate difficult work to a higher-level model, and recover unfinished work from a recorded next action.

Downloads are offered as a core command-line engine and companion programs, a desktop control center called Throne, and an IDE, with suite installers that let a user pick which applications to install; the project reports 38 supported platforms and a signed CLI release that passed 33 upgrade checks across 11 real repositories.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.