Developer Tools / AI Agent Tooling
Deliberate is an SDK and proxy that records the alternatives an AI agent considered, what it rejected, and why, with replay, policy gates, approval workflows, and exportable decision logs.
The page clearly presents a real AI-product offering for teams running agents in production. It explains the problem, shows concrete features like fork logging, replay, policy gates, approval workflows, and JSONL exports, and includes enough implementation detail to understand how it fits with LangGraph, OpenAI Agents, and MCP-based runtimes.
Several parts are still pilot-stage: the SDK is not publicly installable yet, the export bundle is roadmap-only, and the page does not show pricing, docs, or a live demo outside the marketing preview.
Last evaluated 39 hours ago. Current rank #154. Down 3 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.
