Canvas, a multiplayer HTML editor for decks that is agent-agnostic and MCP-first, has been released as a standalone tool with its own Supabase project and auth. The editor supports slide ownership by …
Silica, an open-source agent for notes and codebases, builds a live model of a folder's contents and rolls back any edit that breaks coherence, according to its developer. The local-first tool, compat…
A developer built a template repository for containerized AI development with cross-compatibility, using Docker and VS Code to isolate AI harness CLI interactions and protect the host system from dest…
Jacquard 0.1, a research prototype programming language designed for AI-written, human-reviewed code, has been released with a compact surface syntax, an OCaml checker and CPS interpreter, a C-emittin…
Flow, a compact data pipeline language designed to reduce token usage for large language models, achieves an average 33% token reduction compared to Python, according to developer Pinku. The open-sour…
VibePod released a unified CLI tool called VibePod that runs AI coding agents in isolated Docker or Podman containers with zero configuration, supporting agents including Claude, Gemini, Codex, Devstr…
SynapseOS, an Arch-based operating system developed by GitHub user velle999, integrates a local LLM daemon as a system service that communicates with the shell, compositor, security monitor, network f…
OpenAI has silently reduced the usable context window for its GPT-5.6 Sol model in Codex CLI from 353,400 to 258,400 tokens, a 26.9% cut, according to a bug report filed by a paid subscriber on GitHub…
Developer saadev0 has published a portable setup for OpenCode using the opencode-antigravity-auth plugin, enabling Google OAuth-based access to Antigravity quota for Gemini and Claude models. The conf…
Jerrycan, an AI-native Rust backend framework and generation platform, has been released in version 0.2.0, allowing AI agents to design, generate, verify, and package complete backends without human c…
Web Cloud Studio released Drydock, an open-source Python command-line tool that adds a repeatable Agile and Test-Driven Development process layer to specification-driven development, enabling users to…
Snowflake, a new DCS modding team, is developing open- and closed-source tooling to address common complaints about the Mission Editor, such as lack of undo/redo, limited AI control, and mission data …
Clawk, a new open-source tool, gives coding agents like Claude Code and Codex a disposable Linux VM instead of direct access to the user's laptop, blocking unauthorized network connections and file ac…
MOON YORK GmbH has released node0, a decentralized peer-to-peer protocol and SDK that enables autonomous AI agents to communicate, authenticate, and transact without human intermediaries. The protocol…
ProtoLink, a lightweight Python framework for building distributed, LLM-powered multi-agent systems that implement Google's Agent-to-Agent (A2A) specification, has been released in beta. The framework…
Consortium, an open-source workflow runtime for LLM-powered applications, enables developers to replace a single model call with reliable, auditable ensemble workflows by changing one line of code. Th…
LLM-mock v1.0, a pytest plugin that records and replays OpenAI and Anthropic API calls, has been released. The tool intercepts HTTP calls at the transport layer to capture real API responses once and …
Looped Automation released Looped AF, an open-source agent framework where each AI agent is defined in a single configuration file and runs as a Docker container. The alpha software supports event-dri…
A developer created a custom status line for Claude Code that displays context usage, rate limit bars with reset times, and clickable links to repositories, branches, and tickets. The script uses jq t…
The Device Context Protocol (DCP) v0.3, hardware-validated on ESP32-WROOM-32 and ESP32-S3 boards, enables LLM agents to safely control physical devices using sub-50-byte frames and under 1 KB of RAM. …