Knowledgator released GLiClass, an open-source zero-shot sequence classification model inspired by the GLiNER framework that performs classification in a single forward pass and runs approximately 10 …
Cayu launched as a production agent runtime in Python that gives applications control of the full agent execution lifecycle, including context assembly, tool invocation, durable state, approvals, reco…
Developer AEndrix03 released Graft, an open-source local-first persistent memory tool for AI coding agents that stores fixes, decisions, and project knowledge in SQLite with sqlite-vec and FTS5 and su…
A developer published a minimal Python patcher that disables the Claude Code VS Code extension's automatic file-context attachment by nulling the argument to applySelectionUpdate in webview/index.js, …
A developer-run experiment found that 26 AI agents — spanning a 4-bit quantized 7B model up to Opus 5 — all passed the visible test suite for a seeded greedy-regex bug while all 26 remained broken, wi…
A developer outlined production best practices for LLM observability, arguing that logging only the final model response is insufficient for AI systems. The guidance recommends tracing the full execut…
Thurbeen released Thurbox, an open-source tmux-based TUI and headless CLI for running multiple coding-agent CLIs side by side, each in its own persistent tmux session and git worktree. Thurbox launche…
8Braid released a public visual companion to OpenAI's Navier-Stokes construction that links an offline interactive diagram to a standalone Lean lemma and five checked statements about selected example…
A developer released Plurnk, a homebrewed AI agent harness, on Hacker News' Show HN, claiming it runs as a daily driver on an RTX 5070Ti with 16GB VRAM and a 200MB footprint. Plurnk features determini…
A developer launched Agenttik, a tool for running AI coding agents in parallel across multiple projects and branches, on Hacker News' Show HN. The developer said the project was built from scratch in …
A developer released refactor-like-hermes, a Codex subagent workflow for refactoring large software projects, distilled from lessons learned during Nous Research's Hermes Agent refactor. The approach …
Skillsynchq released txcript, an open-source library and CLI that converts AI coding-agent sessions between harnesses including Claude Code, Codex, OpenCode, and Cursor, carrying over messages, reason…
Adios launched a hosted MCP service that lets coding agents build, preview, debug, and deploy apps from clients including Codex, Claude Code, Gemini CLI, Kimi Code, GitHub Copilot, and ChatGPT. The se…
A developer released sustained_bench.py, an open-source Python script that measures how much local LLM inference throughput on Apple silicon decays over a 30-minute sustained run due to thermal thrott…
A developer released sentinel-imxd, a lightweight log-anomaly detection daemon for the NXP i.MX 8M Plus that runs a TensorFlow Lite autoencoder on the board's Vivante NPU via the VX external delegate.…
Developer GraafHenk released WangNet, a 1.8 MB JSON neural network with roughly 100 lines of pure Python standard-library inference code that adjudicates whether a number is Numberwang across 11 langu…
Moritz Linn has paused Melody Matcher, a neural-network music recommender that used audio embeddings and candidate-conditioned attention over a listener's library, because the model does not work well…
FluidScript, a statically checked scripting language for .NET applications from developer jorgeleo, compiles scripts to verified, deterministic P-code that runs on a purpose-built virtual machine with…
A vLLM contributor published an FP8 multi-token-prediction (MTP) draft stack for vLLM that yields a 6.6% decode throughput gain on modelopt NVFP4 Qwen3.5-family checkpoints. The change quantizes the p…
A developer released minizinc-mcp, an MCP server that exposes MiniZinc constraint solving and optimization to LLM clients including opencode, Claude Desktop, and Cursor, letting agents parse, type-che…