[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-95978":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":9,"totalLinesOfCode":9,"stars":12,"forks":13,"watchers":14,"openIssues":14,"contributorsCount":9,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":14,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":15,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":16,"hasPages":16,"topics":9,"createdAt":9,"pushedAt":9,"updatedAt":18,"readmeContent":19,"aiSummary":20,"trendingCount":14,"starSnapshotCount":14,"syncStatus":21,"lastSyncTime":9,"discoverSource":22},95978,"experiential","experientiallabs\u002Fexperiential","experientiallabs","Experiential is the open source, zero markup gateway for BYOK, self-hosted and 1000+ marketplace models. It learns from your traffic to cut costs, recommend better models, and train a specialized model you own.",null,"https:\u002F\u002Fgithub.com\u002Fexperientiallabs\u002Fexperiential","Python",1933,103,0,19.05,false,"main","2026-09-21 02:04:29","# Experiential\n\n[![gateway latency](https:\u002F\u002Fimg.shields.io\u002Fendpoint?url=https%3A%2F%2Fraw.githubusercontent.com%2Fexperientiallabs%2Fexperiential%2Fbadges%2Fgateway-latency.json)](https:\u002F\u002Fgithub.com\u002Fexperientiallabs\u002Fexperiential\u002Factions\u002Fworkflows\u002Fgateway-latency.yml?query=branch%3Amain)\n\nExperiential is an open source gateway and router for agent workflows:\n\n1. Use hosted, BYOK, and local models through one OpenAI-compatible API.\n2. Control which users and agents can use which models, for which use cases, and how much they can spend.\n3. Turn production traffic into a custom router or model optimized for quality, speed, and cost.\n\n![Experiential workspace usage dashboard showing model traffic, identities, and spend](https:\u002F\u002Fraw.githubusercontent.com\u002Fexperientiallabs\u002Fexperiential\u002Fmain\u002Fassets\u002Fexperiential-workflow.png)\n\n\u003Cp align=\"center\">\n  🌐 \u003Ca href=\"https:\u002F\u002Fplatform.experientiallabs.ai\">Platform\u003C\u002Fa> |\n  📚 \u003Ca href=\"https:\u002F\u002Fplatform.experientiallabs.ai\u002Fdocs\">Docs\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FB6sM8xTVwU\">\u003Cimg src=\"https:\u002F\u002Fcdn.simpleicons.org\u002Fdiscord\u002F5865F2\" alt=\"\" width=\"16\" height=\"16\"> Discord\u003C\u002Fa>\n\u003C\u002Fp>\n\n## Getting Started\n\nStart a local OpenAI-compatible gateway. On first run, the setup wizard uses the shared provider,\nmodel, and reasoning-effort selectors, persists every selected provider connection, then shows\ndefaults for the public alias, identity, and `$50.00` command budget before printing a one-time key:\n\n```bash\npip install experiential\nexp\n```\n\nChoose a public alias such as `opus-5`, capture the issued key, and send a request:\n\n```bash\nexport EXP_GATEWAY_KEY=...\ncurl http:\u002F\u002F127.0.0.1:8000\u002Fv1\u002Fchat\u002Fcompletions \\\n  -H \"Authorization: Bearer $EXP_GATEWAY_KEY\" \\\n  -H 'Content-Type: application\u002Fjson' \\\n  -d '{\"model\":\"opus-5\",\"messages\":[{\"role\":\"user\",\"content\":\"Help me\"}]}'\n```\n\n## Setup \u002F get started with the hosted gateway\n\nPrefer a managed gateway to running one locally? The hosted platform at\n[platform.experientiallabs.ai](https:\u002F\u002Fplatform.experientiallabs.ai) serves the same\nOpenAI-compatible (and Anthropic Messages) API at `https:\u002F\u002Fapi.experientiallabs.ai\u002Fv1`.\nSee [SETUP.md](.\u002FSETUP.md) for copy-paste prompts you hand to your coding agent\n(Claude Code, Cursor, Codex, and similar); the agent runs the setup for you. It\ncollects four prompts:\n\n- Upload your LLM traces as telemetry: create an account instantly from your email, then pull or upload your existing LLM traces onto the platform as telemetry.\n- Connect your inference provider keys (BYOK): create an account, then connect your own OpenAI, Anthropic, Gemini, Azure, Bedrock, Fireworks, or OpenRouter keys for free pass-through.\n- Start calling models on the gateway: make your first `\u002Fv1` call with the OpenAI and Anthropic SDKs using an `xpl_` key, and optionally repoint your existing coding agents.\n- Full onboarding: create an account instantly from your email, connect your keys, import your spend, then repoint every coding agent (Claude Code, Cursor, Codex, Aider, and similar) or Conductor at the gateway.\n\n## Using the API\n\nStart the local gateway with `exp` (or `exp run`); the compiled native data plane\nserves every route on loopback. From Python, load a fitted project router as an\nofficial OpenAI client backed by its own private gateway:\n\n```python\nimport exp\n\nwith exp.load_router(\"my-project\") as client:\n    response = client.chat.completions.create(\n        model=\"my-project\",\n        messages=[{\"role\": \"user\", \"content\": \"hello\"}],\n    )\n```\n\n## Optimize from Traffic\n\nFirst, collect OpenTelemetry traces from your current agent. If you just want to try it out, grab\nthe public [terminal-tasks OTLP dataset](https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fexperiential-labs\u002Fwmo-terminal-tasks-traces):\n\n```bash\ncurl -L -o traces.otel.jsonl \\\n  https:\u002F\u002Fhuggingface.co\u002Fdatasets\u002Fexperiential-labs\u002Fwmo-terminal-tasks-traces\u002Fresolve\u002F540883e451dc13d34fb50fdd36b143cb0f1fb0db\u002Ftraces.otel.jsonl\n```\n\nThen build a project. The build command walks you through providers,\nmodels, and budget, and asks for your trace file:\n\n```bash\n# Build simulation from your agent traces and optimize a router against it\nexp build support-agent\n```\n\nAfter collecting traces from your router, fine-tune an open source model you own using\n[Tinker](https:\u002F\u002Ftinker.thinkingmachines.ai\u002F).\n\n```bash\nexp optimize model support-agent\n```\n\n## Telemetry\n\nAnonymous aggregate PostHog product telemetry is enabled by default. It never includes prompts,\ntraces, actions, observations, paths, model names, credentials, or raw customer content.\n\n```bash\nexp config telemetry status\nexp config telemetry disable\nexp config telemetry enable\n```\n\nThe preference is stored locally in `.exp\u002Fsettings.toml`.\n\n## Development\n\n```bash\nuv sync --extra dev\nuv run ruff format --check .\nuv run ruff check .\nuv run ty check\nuv run pytest -q\n```\n\nRepository and documentation conventions live in [AGENTS.md](.\u002FAGENTS.md).\n","Experiential 是一个开源的、零标记（zero markup）LLM 网关与智能路由系统，用于统一接入和调度 BYOK（自带密钥）、自托管及 Marketplace 中的 1000+ 大模型。它提供 OpenAI 兼容 API，支持细粒度访问控制（按用户\u002F代理\u002F场景\u002F预算）、实时流量分析，并基于生产请求自动优化模型选型、降低成本，还可训练专属微调模型。适用于多模型混合部署、AI 代理工作流编排、企业级 LLM 成本治理与模型可观测性等场景。",2,"trending"]