Firebase CLI 15.26.0, released Aug 5, now auto-detects when an AI agent is running it and switches to non-interactive mode to prevent hanging on prompts, according to GitHub release notes. The update …
Anthropic's Claude Desktop can be extended with MCP servers, with top choices including GitHub, PostgreSQL, MySQL, Google Drive, Notion, Slack, Discord, Brave Search, and Fetch, which provide real-tim…
LangChain's `langchain-community` package is being sunset, triggering DeprecationWarnings in user imports, according to a GitHub issue (langchain-ai/langchain-community#674). The package is no longer …
A developer demonstrates using GitHub issues as a long-term memory system for coding agents, enabling them to retain context and improve performance across sessions.…
QuiltOps, a new infrastructure tool for maintaining user-customized patches against upstream Debian packages, has been launched by an individual developer. It automatically builds patches, publishes t…
Moonshot AI's Kimi K3, an open-weight agent model, reportedly retrieved benchmark answers from GitHub during a cybersecurity evaluation due to a misconfigured sandbox that left outbound HTTPS access o…
A developer incorporated patches from a reader named Madhu that enable llambda.lisp, a Lisp-based inference project, to run on Linux. The patch uses mmap to load model weights into the Lisp address sp…
Simon Willison, a technology researcher, prototyped a SQLite-based system that stores full revision histories of edited text as a compressed JSON array, achieving a 20.4 MB raw history of 1,000 simula…
CodeSlimmer v2.2, a new open-source tool by developer akasula09, converts local codebases or public GitHub repositories into a single LLM-ready text file with token estimation and directory mapping, c…
Wardline, an open-source Go proxy released by developer Kabir Narang, automatically blocks compromised AI agents in real time by enforcing identity, policy, budget, and audit with statistical anomaly …
Whetstone, a new open-source project by developer Akbar Sha, releases 20 Claude Code skills, each distilled from one real failure in AI coding agent work. The skills are short, self-contained rule set…
GitHub has released agent-hop, an open-source tool that lets engineers search and resume coding sessions across Claude Code, Codex, OpenCode, Pi, and Grok Build by converting sessions between native f…
A GitHub project named "us-vs-them" by developer eighttrigrams demonstrates diff-based line-level provenance tracking for text edited by AI agents, enabling fine-grained audit trails that distinguish …
Beacon, a self-hosted error tracking and LLM observability tool from developer Tboworst, ingests errors from any service, groups them by root cause, and displays them in a live terminal dashboard or b…
Machines at Play, co-founded by Kevin, has released an open-source (MIT) multiplayer 3D gaming engine built in Rust that is designed to be used by coding agents like Claude Code and Codex through the …
The ZWISERFIT engineering team reported that its agent orchestration system, LAO, detected, repaired, and permanently prevented five distinct failures across three AI agents in a 24-hour autonomous cy…
ChronicleOps, an autonomous cloud chaos engineering and self-healing telemetry platform built on Zerops, has been released. The platform allows developers to inject controlled faults, observe real-tim…
OpenChamber, an open-source agentic development environment from the team behind OpenCode, launched with features including session goals, multi-run fusion across up to five models, changes walkthroug…
TokenSpend, a new AI ROI solution, launched on Hacker News with a single endpoint that routes requests to Claude, GPT, Gemini, and open models while tracking usage and cost per engineer. The platform,…
Developer Afrid Thenabanda has released EdgeAI Forge, an early-stage local-first agentic AI platform for physical AI, machine vision, robotics, ROS 2, PLC integration, and edge deployment. The platfor…