Results for agentops

TypeScript implementation of the AgentOps SDK

AgentOps observability for ai-squad SDD/Discovery pipelines

MCP index access to the AgentOps Public API.

Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.

MCP index access to the AgentOps Public API.

ai-squad CLI — deploy SDD/Discovery squads. Skills+agents user-global (~/.claude/), hooks per-repo (<repo>/.claude/hooks/) to keep agentops telemetry consistent with hook version.

AgentOps Core - AI agent framework for JavaScript

MCP index access to the AgentOps Public API.

AI agent security scanner — detect secrets before they reach cloud models

Enterprise guardrails, delivery lifecycle, and self-evolution for Claude Code CLI

MCP tool server for running specialist agent CLI programs

Step-by-step observability for MCP agent workflows

OpenTelemetry SpanProcessor for atrib. Reads OpenInference-shaped spans and emits signed atrib records on a parallel pipeline. One integration reaches every framework with OpenInference instrumentation.

Quick check: are you building or spiraling?

Local proxy that intercepts Anthropic API calls, monitors token spend, and optionally routes to cheaper models when budget runs low.

Tool-agnostic watch runtime with transcript providers for coding agents.

Client side token counting & price estimation for LLMs

All-in-one Claude Code token optimization: 17 strategies from LLMLingua, RouteLLM, GPTCache, tokencost, Aider, Letta, SWE-Pruner, AgentDiet, Portkey, Helicone, ccusage, claude-code-router, claude-mem, caveman, ruflo, and gstack. Save 80-95% on tokens.

JavaScript port of tokencost

Calculate token costs across OpenAI and Anthropic models. Zero dependencies, works in Node.js and browser.

HITL infrastructure for AI agents. Your agent calls awaitHuman(), a human reviews via Slack/email/dashboard, agent resumes with a typed response.

Local-first trust report and CI gate for AI agent tooling evidence.

This package captures OpenCode session telemetry and sends it to the Lena AgentOps event ingestion API.

Local-first security and cognitive-risk scanner for MCP tools and agent skills with ToolBOM, attack harness, and policy checks.