Observed Signal · Aug 8, 2026 · Technical Release · Source: DEV Community · Impact: 2/5 · Sentiment: Positive
CHOMATO released as lightweight harness for LFM 2.5
Karol Rybak announced CHOMATO, an open-source lightweight harness for LFM 2.5 that supports branching KV-cache, attaching precalculated context blocks, structured sparse outputs, and running anywhere WebGPU is available. The project includes a live demo and source code published on GitHub under the AGPL-3.0 license; the author notes two additional libraries used are available on their GitHub under MIT. The GUI is primarily diagnostic and the tool aims to run in under 1 GB of RAM.
Open-source technical release for LLM developer tooling that enables low-memory WebGPU execution and structured outputs; relevant to developers but not a major industry-wide platform or policy change.
Track DEV Community Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Karol Rybak published an article introducing CHOMATO on Aug 8, 2026.
- CHOMATO is an open-source lightweight harness for LFM 2.5 with a live demo and source code on GitHub.
- The repository is licensed under AGPL-3.0; two additional libraries used by CHOMATO are available on the author's GitHub under the MIT license.
- CHOMATO is designed to run on backend, frontend, or any environment where WebGPU works and aims to operate in under 1 GB of RAM.
- The GUI is primarily for diagnostics and the engine exposes a sparse (structured) default API mode.
Connected Companies & Entities
6 Entities mapped“DEV Community — A space to discuss and keep up software development and manage your software career...”
“[Powered by Algolia]...”
“Code: https://github.com/3ksoft/chomato (AGPL-3.0)....”
“Neon is the official database partner of DEV...”
“Built on Forem — the open source software that powers DEV and other inclusive communities....”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Local MCP Server with Ollama and ChromaDB
An engineering post‑mortem describes building a local MCP server for codebase memory using Ollama (local LLM hosting) and ChromaDB (vector retrieval) within the open-source zerikai_memory project. The author tested two local models (mistral:7b and ornith:9b) on an 8GB RTX 3050 system and measured latency, synthesis quality, and operational issues. Key findings: mistral:7b is faster and fits 8GB VRAM, while ornith:9b produces denser, more precise briefs given enriched docstrings but has longer cold starts and higher VRAM needs. The team implemented an ollama_semaphore / OLLAMA_MAX_CONCURRENCY gate to avoid GPU saturation during concurrent brief synthesis. The recommended workflow emphasizes docstring enrichment (embedding-docstring → scan_workspace) and advises RTX 3060 12GB as the practical minimum for ornith:9b in production local deployments.
Developer Runs GLM-5.2 LLM Locally on a Laptop
A developer known as Vincenzo (online alias JustVugg) published an open-source project called colibrì on GitHub that enables the 744-billion-parameter GLM-5.2 model to run on a consumer laptop with 12 CPU cores and ~25 GB RAM. The engine leverages the model's Mixture-of-Experts (MoE) architecture by keeping the core weights in ~10 GB of RAM and streaming over 21,000 expert modules (~370 GB) from an NVMe SSD on demand. colibrì is implemented in C, requires no Python or dedicated GPU, and uses caching to speed repeated requests. The proof-of-concept is extremely slow (about 0.05–0.1 tokens/sec) and risks accelerated SSD wear due to heavy disk I/O, but represents a milestone for local AI and digital sovereignty.
Open-source tool enables LLMs to watch videos locally
An open-source project, claude-real-video, enables language models and MCP clients (e.g., Claude Desktop, Cursor) to ingest videos locally by extracting scene-aware, deduplicated keyframes and a timestamped transcript. The tool (MIT license, ~1.9k stars on GitHub) runs fully on the user's machine, offers two MCP-callable tools (watch_video and get_frames), caches analyses under ~/.cache/crv-mcp, and requires Whisper for transcription. Since version 0.8.0 it exposes an MCP server so compatible clients can request videos directly. The author verified end-to-end operation on Claude Code and notes compatibility considerations with the MCP SDK/FastMCP releases.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.