A new independent study by researcher Aleksandr Churilov found that five frontier large language models—Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini, Gemini 2.5 Pro, and DeepSeek V3.2—collectivel…
SynnoDB, a drop-in replacement for DuckDB that transparently accelerates SQL with auto-generated bespoke C++ engines, is now available on PyPI. The project packages the Bespoke-OLAP research into a pr…
Guard-AI, a new security linter from developer Karthik VK, automatically catches AI-generated code vulnerabilities such as hallucinated dependencies, hardcoded secret placeholders, and truncated code …
A developer built four open-source AI tools last year that saw only 20% adoption, then created MCPlex, a stateless HTTP proxy that exposes any REST API as an MCP tool for AI coding agents. The proxy e…
Researchers released OpenLanguageModel (OLM), an open-source PyTorch library for building and pretraining small language models with readable, composable code. The library includes 27 presets across n…
Eventual Inc. released daft-physical-ai, an open-source Python library built on Daft that provides ready-made operations for turning raw robot video into training-ready data, starting with hand tracki…
Refuse, a pre-install security shim that blocks vulnerable package installs before they reach the disk, has launched to address a surge in supply-chain attacks targeting AI coding agents. The tool int…
A developer shipped version 0.2.0 of their agentproof-scan tool, correcting a discrepancy where the README claimed 16 detection families and reasoning-scanning but the 0.1.4 package only had six famil…
A developer discovered a bug in ContextOS, a context operating system for AI coding agents, where the secret detector failed to redact Redis passwords from database URLs because the regex pattern requ…
Flanner.io released v0.7.1 of Flanner, a free, open-source CLI and MCP server that manages planning documents generated by AI agents, versioning every revision and linking each plan to its correspondi…
TreeThink, a new open-source Python library for neural theorem proving, offers modular asynchronous tree search with native integration for formal verifiers in Lean 4, Rocq, and Isabelle/HOL, achievin…
Refuse, an open-source tool that intercepts package manager calls to block vulnerable installs before they execute, launched to address a structural gap in AI coding agent workflows. The tool installs…
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…
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…
A developer built Claude Supervisor, an open-source tool that automatically pauses and resumes Claude Code when usage limits are hit, allowing long-running agentic tasks to complete unattended. The to…
A lawyer-turned-developer open-sourced OpenSymphony, an AI agent framework that enforces personality, governance, and self-evolution through YAML-based souls, a multi-layer governance system, and a to…
LocalMask, a new open-source CLI tool, masks personally identifiable information (PII) and secrets in code repositories before sending them to large language models (LLMs). The tool creates private, m…
Sqlsure, a deterministic semantic checker for AI-generated SQL, catches logical errors like double-counted revenue and exposed patient identifiers that databases and linters miss. The tool, which runs…
A census of 15,382 Model Context Protocol servers found that 47% run remotely, 16% have verified problems such as deleted GitHub repos or deprecated packages, and 9,207 servers have fewer than 10 star…
A developer released E-- (English--), a programming language written in canonical English that compiles deterministically to Python, separating LLM-based code generation from runtime execution to ensu…