Recently Evaluated

A PHP framework built around the Action-Domain-Responder pattern, with a small core and an emphasis on code that humans and agents can both follow.

Open-source Python framework for building multi-agent LLM apps that can run on local models through Ollama or on hosted APIs like OpenAI, Anthropic, and OpenRouter. The repo highlights built-in plugins, workflow orchestration, agent serving over HTTP, and guardrails for tool use.

Python CLI wrapper for Jev that analyzes JSON, NDJSON, JSONC, and text logs with typed AI questions and confidence-aware answers.

Open-source shared memory for AI coding agents. Motif collects sessions from tools like Claude Code, Codex, and Cursor into a self-hosted graph of decisions, files, and session history, with MCP access, recall, and conflict checking.

A free AI visibility checker that audits how a business may appear in ChatGPT, Claude, Gemini, and Perplexity, with a local-business style input flow and an API/docs offering.

A public timeline and dataset of notable AI-involved hacking and cyber incidents, with RSS support and source links for each entry.

A local coding-agent setup that turns Ollama models into a private, verified team of specialist agents for coding workflows. It includes hardware-aware model selection, role assignment, permission-restricted workflows, and validation probes.

Open-source code search for coding agents, built on Jev, with benchmarked speed and token-use gains across Codex, OpenCode, and Claude Code.

AgentTrace is a Python-based observability and runtime self-healing system for AI agent workflows. It logs multi-step tool calls, surfaces latency issues, and attempts to repair malformed LLM tool arguments before they crash a run.

Ambits is a code-reading and search tool for AI agents that adds symbol-aware grep/rg output plus session history tracking so agents can remember what they already read after context compaction.

A blog post from Archestra analyzing Jev on 100 real AI tool calls, with benchmark results, failure analysis, and comparisons against other models used for annotating agent traces.

Local long-term memory for a personal AI that keeps raw conversation logs, timestamps every record, and uses time-aware retrieval plus a small current-topic index.

A Python library for agent evals and guardrails that uses typed decision questions instead of an LLM judge. It supports one-request evaluation for traces, with examples for tool choice, grounding, relevancy, and injection checks.

A local proxy that inspects LLM requests and attachments for secrets before they reach the model, with redaction, rejection modes, and local attachment decoding/OCR.

A CLI and agent skill that checks whether tests actually exercise real behavior, with a TypeSafe API key flow, diff-based audits, and CI-friendly output.

A read-only CLI for querying Kibana/Elasticsearch logs, with a companion agent skill and MCP server for AI assistants.

A TypeScript CLI for AI-native development that scans a codebase, maps dependency graphs and blast radius, and helps AI tools make safer changes with architectural context.

A GitHub engineering article describing how the Copilot team ported a large production runtime to Rust with Copilot’s help, including the migration strategy, interop, caching, static analysis, and model selection.

A self-hosted mobile web UI for watching terminal-based coding agents, replying to blocked prompts, and getting push alerts from a phone.

Open-source native macOS reading workspace for PDFs, EPUBs, and TXT files with highlights, notes, inline rewriting, book chat, browser panes, and local-first storage.

Cotyper is a coding agent/devtool aimed at fast iteration and working over existing GitHub projects. The page positions it as faster than Codex and lists supported tools including Claude Code and Codex, plus a GitHub connection flow.

A utility for AMD GPU users running local AI on Windows or Linux. It detects the GPU, applies the right HSA_OVERRIDE_GFX_VERSION setting, offers health checks, and benchmarks Vulkan vs. HIP/ROCm for local LLM setups.

KillSwitch is an esoteric programming language aimed at breaking LLMs and coding agents. The site includes a language overview, interpreter/specification/examples, and benchmark references.

An interactive 3D Sun-Earth-Moon simulator that teaches kids how the Moon phases change, with playback controls, orbit views, and learning prompts.