Parselbox, an embeddable Python sandbox for AI agents, launched on Hacker News, enabling agents to call MCP servers, APIs, and shells as native Python objects in a single Deno and Pyodide process (~16…
Talvik, Inc. has released MAK4I, an open protocol for packaging, identifying, versioning, sharing, injecting, and reusing AI artifacts across models, platforms, and organizations, currently in Phase 0…
Lixxx1 released dsh-vscode, a VS Code extension that brings DeepSeek Harness (DSH) into a right sidebar, allowing developers to inspect, change, and verify code without leaving the editor. The extensi…
A developer has documented a self-hosted AI assistant setup running Ollama, Open WebUI, and Caddy in Docker on a $9 Hostinger KVM2 VPS with 2 vCPUs, 8 GB RAM, and no GPU. The setup achieves token gene…
Syndicate OS, a self-hosted multi-agent federation developed by Kevin-the-minion, launches with a one-command setup that deploys a fleet of autonomous agents on local hardware, featuring a board UI, t…
Agent Office, a multi-agent workspace manager built on Pi, orchestrates AI coding agents with tick-based scheduling, priority queues, inbox IPC, cross-agent file access, watchdog monitoring, cron jobs…
Locus Engine, a pure Rust AST safety firewall for AI coding agents, claims deterministic invariant checks in under 0.05 ms, with benchmarks showing 9.04 µs average latency for its 6-pass AstGuard veri…
A developer released gpu_retired_pages.py, a read-only Python script that uses NVML to dump retired GPU memory pages with retirement timestamps, a feature nvidia-smi lacks. The tool auto-detects times…
Mcploitable, a new open-source project by agileAlligator, provides seven deliberately vulnerable Model Context Protocol (MCP) servers and three guided simulations that together cover the OWASP Top 10 …
AI.DIY, an open-source AI workspace from Cubinghackerz, lets users run an AI chat and agent environment entirely in the browser with local-first storage, bring-your-own-key provider support, and an in…
ContextForge, a pre-alpha context engineering platform for AI-assisted development, released version 0.4.2 as its first public-release candidate. The tool scans local repositories to build determinist…
Lunar, a terminal coding harness extensible via Lua, has been released as an open-source tool on GitHub by developer gszr. It provides four tools—read, write, edit, and bash—and supports any OpenAI Ch…
DeepSeek Harness (DSH) has released dsh-univer-office, a modular office plugin that enables the AI agent to create, edit, inspect, and deliver spreadsheets, documents, presentations, databases, and ca…
Developer Dmitrii Malakhov released grok-ultracode, an open-source plugin that brings Claude Code's ultracode workflow pattern to xAI's Grok Build CLI, enabling the agent to author and launch determin…
Bulwark Gateway, a self-hosted fail-closed security proxy for LLM agents, intercepts and validates tool calls between users and LLM backends, blocking threats immediately with 400+ detection patterns …
A new CUDA kernel correctness harness compiles kernels with nvcc, loads them into Python via ctypes, and checks outputs against NumPy baselines, with timing via CUDA events. All 23 tests pass on an NV…
David, a solo developer, launched an open source video editor on Hacker News that can be controlled via an LLM, allowing novice to intermediate editors to use natural language commands instead of navi…
A developer known as djhallaaaa has released a Claude Code skill that organizes DJ libraries for rekordbox and Serato. The skill learns from a user's existing playlists to sort unorganized tracks by g…
Alibaba released ANOLISA, an open-source agentic operating system layer for AI Agent workloads, featuring a terminal interface (cosh-ng), token compression (Token-less), observability (AgentSight), an…
OpenAI's Codex CLI version 0.147.0 lacks explicit cache controls for GPT-5.6 Sol on Amazon Bedrock, causing cache-write tokens to account for about 85% of estimated spend, with 171.94 million cache-wr…