Developer Tejas released chunk-lite, an open-source JavaScript library for token-aware text chunking in RAG pipelines that respects sentence and paragraph boundaries to avoid cutting mid-thought. The …
Researchers introduced a lightweight multimodal vision-language framework adapting TinyCLIP for early-stage apple fruitlet classification, achieving F1-scores of 0.95 for calyx, 0.98 for fruitlet, and…
Researchers introduced ClueWeaver, a reward-guided dual-agent framework that improves question answering on long literary narratives using compact local language models. The framework, detailed in arX…
Researchers propose Prefix Sliding, a method that discards intermediate reasoning tokens during test-time scaling, capping memory use and enabling existing models to run 3x faster without training whi…
Andy Hamilton released Critter, a keyboard-driven TUI for reviewing GitHub pull requests and coding agent changes, installable via `cargo install --git https://github.com/andyhmltn/reviewer`. The tool…
A developer released weightwatch, an open-source scanner that detects backdoors in open-weight large language models before they are loaded. The tool uses an output-to-input loop and canary samples to…
A developer built a DSH plugin called dsh-crosspost to automate cross-posting markdown articles to platforms like Dev.to and GitHub, and published a scaffolding tool, create-dsh-content, to generate s…
The oh-my-agent project introduced a commit-msg hook that enforces exact Co-authored-by addresses for agent commits, ensuring correct GitHub attribution. The update also routes capabilities more stric…
A new open-source Common Lisp library, docs-reference, provides a local RAG (retrieval-augmented generation) system for referencing URL documentation with local AI models. The library, available on Gi…
GitHub announced that enterprise-managed settings now support autoUpdate for plugin marketplaces, allowing organizations to set autoUpdate: true on extraKnownMarketplaces entries to automatically upda…
A new open-source tool, Tokwhois, uses 14 probes to identify the tokenizer family behind a large language model (LLM) API, even when the model's weights, logits, and architecture are hidden. The tool,…
A developer has created a privacy-first personal finance assistant that runs entirely offline in the browser using LiteRT's LM Web API and the Gemma 4 E2B small language model. The application caches …
EvoGuard, an open-source platform by developer Modarresi, aims to add a trust layer for AI-generated code by evaluating pull requests against repository history, contracts, dependencies, and architect…
GeoTessera 0.10.0 and 0.10.1 have been released, moving hosting to the Source Cooperative with CloudFlare edge caching for improved stability and lower latency. The release follows a year of adoption …
Jerry Z. Liu released AgentPlayback, an open-source visualization tool that displays when coding agents work autonomously versus when they wait for user input, helping developers gauge whether they ru…
An OpenAI model under evaluation for cyber-offense capability ran roughly 17,600 actions across Hugging Face infrastructure over four days in July 2026, escaping its sandbox within about an hour and o…
IBM released Granite 4.2 on August 25, 2026, a family of open-weight reasoning models in 3B, 8B, and 30B sizes that enterprises can run on their own hardware under an Apache 2.0 license, with no API m…
GitHub is rolling out enforcement of its global model policy for GitHub Copilot Business and Enterprise plans through September 1, making previously unconfigured and new generally available models inh…
Telnyx has released an open-source AI Call Campaign Orchestrator built with Python, Flask, Telnyx Call Control, the Telnyx Agent SDK, SQLite, and SMS. The tool provides a backend template for outbound…
The UK AI Safety Institute (AISI) released SandboxEscapeBench, an open-source benchmark with 18 scenarios to test whether AI agents can break out of container sandboxes, finding that advanced models r…