Chain-shield released AI Agent Audit, an open-source Rust tool that uses large language models to audit Solidity smart contracts for security vulnerabilities. The tool generates proof-of-concept explo…
Telnyx released an AI Customer Churn Predictor that uses its AI Inference API to analyze call and message patterns via Telnyx APIs, predicting churn risk and suggesting interventions. The open-source …
A developer orchestrated a whimsical zoo escape scenario called 'Operation: Wild Freedom' using a nested team of animal subagents. The plan involved delegating tasks to ground and marine ops branches,…
Guardian, an open-source user-space firewall for AI agents, has released v0.1.0, intercepting and evaluating agent actions with a deterministic policy engine. In testing, it reduced prompt-injection a…
A developer created a Starship prompt segment that displays the current Neon branch linked to a directory. The segment uses the Neon CLI's `neon status --current-branch` command, which reads a local `…
Khazad, a transparent semantic cache for LLM API calls built on Redis Vector Sets, reduces API calls by ~50% and latency by ~96% by intercepting HTTP traffic at the transport layer without code change…
Xenoeye, an open-source network traffic analyzer that avoids AI, uses netflow protocols, PostgreSQL or ClickHouse, and Grafana for visualization. It features monitoring objects for filtering flows, ag…
CORE, an open-source governance runtime for AI-assisted software development, enforces deterministic constitutional rules to block unsafe AI actions before execution. The tool, available on PyPI, prov…
Fleet, a local-first web console for managing Dockerized Hermes AI agents, has been released as an open-source tool. It enables operators to create, configure, monitor, and operate Hermes and Nemo Her…
A developer released an unofficial community plugin for Claude Code that replaces the official TypeScript LSP with a faster native Go implementation backed by TypeScript 7's `tsc --lsp --stdio`. The p…
A developer merged Andrej Karpathy's CLAUDE.md and LOOPS.md with a battle-tested system prompt used in over 100 full-stack apps, creating a 35-rule, 6-tier framework for reliable AI agent behavior. Th…
The Halgorithem Project has launched an open-source tool for detecting AI hallucinations, aiming to improve documentation quality in open-source software. The project provides templates, guides, and t…
A developer released Context Warp Drive, an open-source tool that deterministically folds LLM agent context without summarization calls, achieving ~90% cache-hit rates in production Claude workloads a…
A developer released AST-guard, an open-source tool that uses deterministic abstract syntax tree analysis to detect reward hacking in AI-generated code, achieving 96.2% recall on a benchmark of reward…
A developer merged Andrej Karpathy's CLAUDE.md principles with a battle-tested system prompt used to build over 100 full-stack apps in under 12 months. The resulting system prompt enforces strict scop…
Nansense, a new interactive PyTorch debugger, allows developers to pause training, step batch-by-batch, and time-travel to different epochs while visualizing activations, gradients, weights, and optim…
A new benchmark, dspy-security-bench, reveals that DSPy prompt optimization degrades adversarial robustness against harder prompt-injection attacks. Testing with AgentDojo's attack suite, optimizers l…
An open-source coding agent called Relay has been released, supporting non-mainstream and Chinese LLM providers like DeepSeek, Qwen, and GLM. The Electron app offers chat and code workspaces with file…
KaliCart Bridge, a free WooCommerce plugin, makes product catalogs machine-readable for AI shopping agents without requiring an API key or cloud service. It exposes structured REST endpoints and disco…
Developer John Pellew launched Katra, an open-source self-hosted memory appliance for AI agents that provides episodic recall, semantic search, knowledge graphs, and temporal analysis via the Model Co…