NInfer, a from-scratch C++/CUDA inference engine, achieves up to 1,313.8 aggregate decode tokens per second on a single NVIDIA GeForce RTX 5090 for the Qwen3.6-35B-A3B model at concurrency 8, with the…
Bernstein, a deterministic orchestrator for CLI coding agents, is now in beta, enabling users to run 44 CLI coding agents from a single scheduler. Developed by sipyourdrink-ltd, Bernstein coordinates …
A developer has published a personal log documenting AI persona speech patterns and drift analysis, focusing on how iterative updates to LLM weights and system prompts cause stochastic drift that erod…
NexusMem, a local memory tool for coding agents, records shell commands, git history, and project docs into a SQLite database, serving ranked, token-budgeted slices on demand. The tool, requiring Node…
Developer Mohamed Lahfir released agent-desktop, an open-source Rust-based CLI that lets AI agents automate desktop apps, including Chromium-based ones, with claimed reliability improvements over exis…
Supervice, a zero-dependency, pure-Python process supervisor for Unix-like systems built on asyncio, has been released on GitHub, offering automatic restart, health checks, process grouping, hot confi…
WMTrace, a new open-source forensic workbench for LLM text watermark detection, launched on Hacker News, offering scheme-aware analysis with evidence grades and abstention rather than opaque AI scores…
A developer has published a blueprint for AgentOS, a model- and runtime-agnostic control plane that enables humans to delegate goals to autonomous agents while maintaining bounded authority, cost, and…
Ramabana, a new coding agent from developer Vedic Reader, is now available via pip, featuring a host that coordinates policy, tools, memory, and routing, with models loaded through the rishi tool supp…
Dictata v0.1.0, a 100% local system-wide voice dictation app for Windows built in Rust, transcribes speech via whisper.cpp and offers optional LLM cleanup, with no data leaving the machine. The releas…
An exploratory research prototype called The Commons found that externally inherited model-generated information can improve or impair later language-model inference, with preserving evidence behind a…
Talos, an open-source autonomous agent from talos-agent.ch, runs on a user's own machine and executes tools only after a deterministic security kernel approves each action via a capability token valid…
Macsomnia, a new macOS menu-bar app by developer iamdadzilla, lets users close their MacBook lid while keeping long-running light jobs such as AI agents, builds, and downloads alive by disabling clams…
Kvcachescope, a logical memory profiler and state inspector for PagedAttention inference engines such as vLLM and SGLang, exposes KV cache leaks that standard GPU profilers like nvidia-smi miss by hoo…
Claude Fable 5, an AI model, invented, built, and played a CLI-based tactics game called SHOVE until it judged it genuinely fun, iterating across six versions and six logged play sessions totaling 22 …
A developer benchmarked the Qwen3.8-27B model with NVFP4 quantization and multi-token prediction (MTP) on an RTX 5090, comparing tier configurations and sweeping spec-draft-n values at 64K context. Th…
Tracepaper, an open-source MCP server that gives AI agents a visual canvas for drawing HTML frames and receiving human feedback via pinned comments, is now available via a one-line install with Bun 1.…
Coroot released rca-lab, an open-source failure lab that runs real, reproducible incidents on a live Kubernetes cluster to test root-cause-analysis tooling, including AI-based systems. The lab deploys…
A developer created review-with-me, a Claude Code skill that runs an automated code review in the background, quizzes the human on the diff, and then reconciles the findings with the human's answers b…
A developer has released an open-source, tool-agnostic system for agentic task management that runs continuously in AI conversation threads, using an append-only task log database and a schema loaded …