Developer Tools / AI Safety / LLM Guardrails
A Python filter layer for LLM apps that evaluates responses against a Lean-verified Scherf logic backend and can pass, flag, correct, or block output.
The page clearly describes an AI-adjacent developer tool with a concrete purpose: filtering LLM output using a verified logic layer. The README shows installation, a quick-start example, the available actions, and how the checker works, which is enough evidence for a useful public listing. It also has a distinctive angle—formal verification plus claim extraction for safety and user-objectification concerns—that makes it stand out from generic moderation tools.
The crawl gives a strong overview, but it still leaves some practical details unclear: how well the claim-extraction step works in real usage, what kinds of models or runtimes it supports beyond the shown Python API, and how developers would configure or extend the policy in a real application.
Last evaluated 15 hours ago. Current rank #285. Down 2 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
An OWASP incubator project that protects AI agent memory from prompt injection, secret leakage, and tampering. It includes a Python library, policy-based controls, benchmarks, and integrations for agent frameworks like LangChain and AutoGen.
CLI for catching AI-generated code smells and regressions in code. It scans changes with 40+ rules across 7 languages, offers fixes, CI gating, hooks, and MCP tools.
