The loomcycle memory architecture, as of v1.75.0, spans five storage planes—key/value, vector, SQL Memory, chunked-graph Documents, and an entity graph—with four scopes (agent, user, tenant, global) a…
LoomBoard v0.1.2, a desktop chat app for the loomcycle agentic runtime, has been released with four packaging options including a Tauri v2 native desktop app, an npm CLI runner, an embeddable React co…
Loomcycle released v1.3.0 with Bashbox, an in-process shell sandbox that runs scripts without spawning host processes, using gbash. It enforces read-only volumes and blocks unknown commands, with opti…
Loomcycle v1.5.0 enables co-authoring between agents and humans by introducing user-scoped MCP dispatch, config-declared static principals, and deep-merge configuration. The update allows agents and h…
A developer upgraded a TrueNAS NAS with an AMD Ryzen 7 8700G APU and 96 GB DDR5 for local LLM inference, achieving 13-15 tok/s on gemma4, after rejecting pricier options like NVIDIA DGX Spark and Mac …
Loomcycle released v1.1.1, enabling interactive agentic sessions over gRPC and TypeScript/Python adapters. Third-party apps can now start interactive runs, push operator messages mid-flight, survive c…
Loomcycle v1.1.0 introduces Filesystem Volumes, replacing the global jail with per-agent read-only or read-write filesystem roots. The update enforces spawn confinement, removes legacy jail environmen…
Claude Code orchestrated a 10-agent code review of loomcycle via MCP fan-out, with reviewers running concurrently inside loomcycle and findings consolidated into a report. The review covered 86 files …
Loomcycle's Web UI v0.26-v0.29 introduces a live agent terminal enabling mid-run steering, persistent interactive runs, inline interruption answers, and a terminal interface. The update includes cross…
A genetic algorithm over forkable AgentDefs successfully demonstrated cross-instance mid-run snapshot and resume across five loomcycle releases. The experiment evolved three genes (creativity, courage…
JobEmber replaced four hallucinating LLM-based batch orchestrators with deterministic code-js agents, eliminating ~8,000 tokens per run and fixing a prompt-violation bug. The migration uncovered two l…