Developer Tools / Security / AI Agent Monitoring
Bastiontrace is a Python library for analyzing AI agent tool-call traces to locate prompt injections, identify where they landed, and map the resulting blast radius.
The page clearly describes an AI-adjacent developer tool with a concrete purpose: forensics for injected AI agents. The README shows install and usage commands, explains the trace format, and demonstrates both analysis and hardening workflows, giving enough evidence for a solid public listing.
The snapshot doesn’t show release history, maintenance activity, or broader integration details beyond a Bastion trilogy and a JSONL-based workflow. It also doesn’t make clear which agent frameworks or trace sources are supported besides the included examples and the bastionprobe handoff.
Last evaluated 16 hours ago. Current rank #359. Down 4 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.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
