A developer created a three-bot system that monitors Telegram OSINT and geopolitics channels, filters messages through keyword and LLM evaluation, and automatically posts approved stories to Bluesky w…
Guardog, a zero-copy C/Python DFA engine, scrubs logs at 571 MB/s, operating 14.4x faster than standard Python regex by bypassing the GIL and using in-place memory mutation. The engine is available fo…
Memoriq, an open-source encrypted vault for saving and searching AI chats from ChatGPT, Claude, Gemini, and Grok, launched on Hacker News. The tool encrypts chat content in the browser before upload, …
A new open-source C# tool, SemanticSourceCode, enables local semantic code search using Ollama or LM Studio for embeddings and SQLite for vector storage. The tool analyzes C# code structure, supports …
Regentix, a policy enforcement gateway for LLM tool execution, uses Rego-based governance to intercept and validate MCP requests from clients like Claude Desktop before execution. The system combines …
Developer Raine released consult-llm, an open-source tool that lets AI agents query other models for second opinions during coding tasks. The tool supports multiple providers including GPT-5.5, Gemini…
Jesse Vincent released Superpowers, a software development methodology for coding agents that enforces a structured workflow of specification, design, and subagent-driven development. The tool is avai…
Agentify has forked the archived TensorZero project, which raised $7.3M, and released Agentify Gateway, an open-source LLM gateway with observability, evaluation, optimization, and experimentation fea…
Agent Gate, a deterministic CI firewall for AI-generated pull requests, has been released as a pre-release v0.1.0 on GitHub. The tool blocks PRs that violate contracts, escalate workflow permissions, …
Loopy, a local terminal meta-agent that watches Claude Code and Codex sessions to identify repetitive patterns and propose automation loops, has been released. The tool aims to help developers shift f…
ScopeKit launched a new tool that creates task-specific context packs for AI coding agents, providing relevant files, symbols, tests, and relationships for a given task. The tool claims to reduce cont…
Open-Cowork, an open-source alternative to Claude Cowork, launches as a cross-platform agentic coworker that automates computer tasks via screen observation and action. The tool supports bring-your-ow…
A GitHub user submitted a pull request to fix a race condition in Home Assistant's SmartThings integration when turning on Samsung air conditioners. The fix ensures the turn-on command completes befor…
ScreenMind, an open-source AI memory tool, analyzes every screenshot locally using Gemma 4 on a 4GB GPU, offering 100% private, searchable screen history as a privacy-first alternative to Microsoft's …
LazyOwn RedTeam Framework, the first RedTeam framework with an AI-powered command and control system, has been released. It includes rootkits, undetectable implants for multiple operating systems, and…
Visa released an open-source vulnerability discovery harness called VVAH that uses frontier AI models from Anthropic and OpenAI to automate security testing. The tool employs multi-agent deterministic…
OpenDevOps, an open-source multi-cloud DevOps agent for AWS and Azure, was released, enabling incident investigation with any LLM via LiteLLM. In benchmarks, it found root causes for 9 out of 10 incid…
A new OpenCode skill enforces a red-test-first workflow for bug reports, requiring the agent to reproduce the bug, write a failing test, log it, and only then propose a fix. The skill, available on Gi…
YC W26 batch startup Approxima open-sourced its agentic QA tool under MIT license, enabling self-hosted web agents to follow and verify user journeys. The tool features explore mode for automatic step…
GEDD is a new open-source framework that enables domain experts to systematically review AI agent behavior and convert their observations into automated evaluation criteria. The tool provides a web-ba…