AutoGPT 是面向自主智能体的开源平台,支持用自然语言或可视化流程创建、运行和管理能够持续执行任务的智能体。
关于 Openlit
Open source Agent Harness Engineering Platform | OpenLIT OpenLIT Website / Home Open Source / Website / Home … Get Started Search Home Home Pricing Pricing Enterprise Enterprise Compare Compare Harness Harness Blogs Blogs Videos Videos About About Docs Docs Otter Open source Agent Harness Engineering Platform OpenLIT is an open-source agent harness engineering platform: OpenTelemetry-native agent observability, evals, guardrails, prompt management, and cost and GPU monitoring for AI agents and coding agents. Free to self-host under Apache 2.0. Documentation View Demo Development Production Instrument Develop Manage Observe Improve Select a stage to preview Development Production Instrument Develop Manage Observe Improve Select a stage to preview Trusted & used by developers and engineers at Agent observability for every LLM call, tool call, and agent step Trace, evaluate, and improve the harness around your agents: LLM tracing, agent evals, prompt management, and model comparison from prototype to production. LLM tracing ↗ OpenTelemetry LLM tracing for every call, tool, and retrieval. Filter by user, session, cost, latency, or metadata. $ pip install openlit · openlit.init() chat.completion 1.82s tool.retrieve 0.64s agent.step 0.41s $0.012 1.2k tok ok LLM evaluation ↗ LLM evaluation with LLM-as-a-judge, heuristics, or human review on production traffic or experiments. LLM execution Evaluators Accuracy 87% Relevance 92% Safety pass Latency · 412ms Cost · $0.004 Prompt management ↗ Prompt Hub for prompt management and versioning. Deploy and roll back prompts without shipping app code. support-agent v3 · prod You are a helpful support agent. Answer using the docs context: {{context}} Keep answers under 120 words. Cite sources when possible. Variables {{context}} {{user_name}} Deploy prod · staging rollback ready v1 v2 v3 Model comparison ↗ OpenGround model comparison playground. Test prompts on real inputs and compare LLMs side by side. Prompt: Summarize this support ticket… fable 1.1s $0.003 Sol 0.8s $0.002 AI agent monitoring ↗ AI agent monitoring for coding agents and tool loops. See tools, cost, and outcomes in one view. 1 planner 2 tool.call 3 writer $0.18 3 tools API key management ↗ Vault for LLM API key management. Store and rotate OpenAI, Anthropic, and other secrets outside app code. OPENAI_API_KEY •••• ANTHROPIC_KEY •••• DB_URL •••• AES-256 rotated 2d ago Cost & latency ↗ Track spend, latency, and quality for AI workloads so you can improve cost an
访问提示
本站仅提供官网信息与访问导航,不代表对该网站的产品、服务或交易作出担保。访问外部网站时,请核对网址,注意账号和财产安全。
同类型网站
查看分类百川智能发布的金融大模型,金融场景能力领先GPT-4o近20%
Build a Large Language Model (From Scratch) 是一款AI 大模型方向的 AI 工具,适合主流大语言模型与开源模型。
支持多 AI Agent 框架的可视化管理面板,支持 OpenClaw 和 Hermes Agent 双引擎,内置智能助手一键安装诊断