Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-09-03 · source-backed
Released September 3, PR #2206 confines storage names against directory traversal, confines symlink targets to configured storage directories, requires API keys for non-loopback server bindings, authenticates the Ollama routes, and defaults the REST server to loopback port 8080. Anyone who exposed a Fabric REST server on a LAN interface before this was running an open proxy to their local Ollama instance.
Each link below shares sources, entities, or timing with this story.
Triple-stream retrieval (BM25 keyword, vector embeddings, knowledge-graph traversal) fused via Reciprocal Rank Fusion on the iii engine, with SQLite for state and an in-memory vector index, no external database. The economic claim: ~170K tokens/year (~$10) versus ~650K tokens...
A Chinese lab shipped a runtime that manages two American coding agents as subagents, and it went from repo creation to 145,439 stars in four days. deepseek-ai/deepseek-harness published dsh-v0.1.0-rc.7 at 12:01 UTC today, its first tagged release since the repo appeared on Au...
Three moves, two days, no coordination between them. August 10–11: GitHub shipped Ollama as a BYOK provider inside Copilot for JetBrains (GitHub Changelog). Unsloth released Unsloth Desktop with a command literally named unsloth start claude, which points Claude Code and Codex...
The July 6 release delivers nearly 90% faster Gemma 4 token generation through multi-token prediction with automatic draft-length tuning, on by default, output-preserving, no config (Ollama). It also adds MLX-engine support for more model families and flash attention for older...
From the Fabric creator: a complete personal agentic AI system built natively on Claude Code's hook system. Memory, skills, routing, context management, and self-improvement. V3 rebuilt to scale through parallelism. Free, open-source, positioned as the "anti-gatekeeping AI pro...
I keep seeing the same pitch from different repos and it's starting to feel coordinated even though it isn't. nanocoder's tagline is "owe nothing to anyone." AnythingLLM's is "stop renting your intelligence, own it." Kaku and Kilo are circling the same idea. Keep your code and...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.