A developer has released Mocca, an open-source wrapper for Claude Code that puts plugins at the center of the experience, featuring a marketplace for discovering and installing plugins with dedicated …
University of Illinois Urbana-Champaign researchers have released an open-source AI teaching assistant on HuggingFace that runs 11 separate models in parallel for text/image retrieval, generation, mod…
Capital One released VulnHunter, an open-source agentic AI security tool that simulates attacker behavior to identify exploitable vulnerabilities in source code and propose evidence-backed fixes. Buil…
An open-source AI agent called SAM that runs on a user's own machine is now available, offering a free, private team of AI agents that can research, remember, and take real action on the computer. The…
A new technique called Cache Tree and Tail Prompt Optimization improves LLM efficiency by reusing KV cache across multiple conversation branches, reducing redundant computation. The approach, describe…
RepoMap, a new open-source tool, generates interactive architectural maps of code repositories without sending source code to an LLM, reducing token usage and enabling faster architectural reasoning f…
LingBot-Map, a feed-forward 3D foundation model for streaming scene reconstruction, achieves state-of-the-art performance at approximately 20 FPS on 518×378 resolution over sequences exceeding 10,000 …
AegisDB, a self-hosted memory database for AI agents, is now available as a single dependency-free C binary that provides durable, searchable long-term memory with multi-tenant auth, encryption at res…
The Little Book of Reinforcement Learning, a short introduction to RL from basics to applied algorithms, is available on GitHub with PyTorch implementations and supplementary proofs. The book, authore…
ReasonGate, an open-source explainable security gate for LLM applications, blocks prompt injection attacks by inspecting user prompts, retrieved context, and model outputs, providing an auditable reas…
A hardware-software co-design prototype called PIM-HBM explores zero-copy memory view fusion and fault telemetry for LLM training, using JAX/XLA integration and branchless CUDA kernels to mitigate com…
Skyportal released an open-source Python SDK and persistent terminal client for its AI infrastructure platform, enabling developers to interact with the SkyPortal API for tasks such as headless agent …
SignalPilot-Labs released a PDF showing that OpenAI's GPT 5.6 solved all International Mathematical Olympiad 2026 questions without human steering, marking the first time an AI has achieved a perfect …
Piebald AI has released a repository tracking Claude Code's system prompts across 237 versions since v2.0.14, now covering 515 prompts as of Claude Code v2.1.211 (July 15, 2026). The repository, updat…
A24 Labs released puffgres (beta), a logical replication service that mirrors Postgres entities in turbopuffer, eliminating data drift by making Postgres the source of truth and automatically syncing …
GrapeRoot released Webify MCP, an open-source tool that achieves 91% of Deep Research quality at 5% of the cost, working in Claude Code, Cursor, VS Code, Windsurf, and Zed. The tool uses two commands—…
L3 Simulator, an open-source Node.js tool, orchestrates AI coding agents over GitHub issues by labeling issues `ready` to trigger automated planning, coding via Claude Code or Codex, and PR creation, …
A developer quantified overused words in Claude Code's responses by analyzing 140MB of session transcripts and comparing word frequencies against Stack Overflow comments, finding that 'load-bearing' a…
A developer known as Vhyrro published a comprehensive primer on programming with large language models, covering how LLMs work, agent loops, MCPs, and skills, along with practical do's and don'ts. Mat…
Latch, a lightweight hybrid post-quantum proxy server, secures legacy TCP traffic against interception and future quantum cryptanalysis using X25519 and ML-KEM-768 key exchange, with features includin…