{ "schemaVersion": "1.0", "item": { "slug": "cascadeflow", "name": "cascadeflow: Cost + Latency Reduction", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/saschabuehrle/cascadeflow", "canonicalUrl": "https://clawhub.ai/saschabuehrle/cascadeflow", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/cascadeflow", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "agents/openai.yaml", "references/clawhub_publish_pack.md", "references/market_positioning.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "cascadeflow", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-04T17:38:38.346Z", "expiresAt": "2026-05-11T17:38:38.346Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow", "contentDisposition": "attachment; filename=\"cascadeflow-1.1.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "cascadeflow" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/cascadeflow" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/cascadeflow", "agentPageUrl": "https://openagent3.xyz/skills/cascadeflow/agent", "manifestUrl": "https://openagent3.xyz/skills/cascadeflow/agent.json", "briefUrl": "https://openagent3.xyz/skills/cascadeflow/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "CascadeFlow: Cost + Latency Reduction | 17+ Domain-Aware Models + OpenClaw-Native Events", "body": "Use CascadeFlow as an OpenClaw provider to lower cost and latency via cascading. Assign up to 17 domain-specific models (for coding, web search, reasoning, and more), including OpenClaw-native event handling, and cascade between them (small model first, verifier when needed). Keep setup minimal, then verify with one health check and one chat call." }, { "title": "Why Use It", "body": "Reduce spend with drafter/verifier cascading.\nRun 17+ domain-aware model assignments (code, reasoning, web-search, and more).\nSupport cascading with streaming and multi-step agent loops.\nHandle OpenClaw-native event/domain signals for smarter model selection." }, { "title": "Security Defaults", "body": "Install from PyPI and verify package artifact before first run.\nKeep the server bound to localhost by default.\nUse explicit auth tokens for chat and stats endpoints (recommended for production).\nExpose remote access only behind TLS/reverse proxy with strong tokens.\nUse least-privilege provider keys (separate test keys from production keys)." }, { "title": "How It Works", "body": "OpenClaw sends requests to CascadeFlow through OpenAI-compatible /v1/chat/completions.\nCascadeFlow reads prompt context plus OpenClaw-native event/domain metadata (for example metadata.method, metadata.event, and channel/category hints).\nCascadeFlow selects a domain-aware drafter/verifier pair (small model first).\nIf quality passes threshold, drafter answer is returned (cost/latency advantage).\nIf quality fails threshold, verifier runs and final answer is upgraded.\nThe same cascading behavior is supported for streaming and multi-step agent loops." }, { "title": "Advantages", "body": "Lower average cost by avoiding verifier calls when not needed.\nLower average latency for simple and medium tasks.\nBetter quality on hard tasks through verifier fallback.\nBetter operational handling through OpenClaw-native event/domain understanding." }, { "title": "Quick Start", "body": "Or ask your OpenClaw agent to set it up for you as an OpenClaw custom provider with OpenClaw-native events and domain understanding.\n\nInstall and verify package source:\n\npython3 -m venv .venv\nsource .venv/bin/activate\npython -m pip install --upgrade \"cascadeflow[openclaw]>=0.7,<0.8\"\npython -m pip show cascadeflow\npython -m pip download --no-deps \"cascadeflow[openclaw]>=0.7,<0.8\" -d /tmp/cascadeflow_pkg\npython -m pip hash /tmp/cascadeflow_pkg/cascadeflow-*.whl\n\nOptional variants:\n\npython -m pip install --upgrade \"cascadeflow[openclaw,anthropic]>=0.7,<0.8\" # Anthropic-only preset\npython -m pip install --upgrade \"cascadeflow[openclaw,openai]>=0.7,<0.8\" # OpenAI-only preset\npython -m pip install --upgrade \"cascadeflow[openclaw,providers]>=0.7,<0.8\" # Mixed preset\n\nPick preset + credentials:\n\nPresets: examples/configs/anthropic-only.yaml, examples/configs/openai-only.yaml, examples/configs/mixed-anthropic-openai.yaml\nProvider key(s): ANTHROPIC_API_KEY=... and/or OPENAI_API_KEY=... (required based on selected preset)\nService tokens: --auth-token ... and --stats-auth-token ... (recommended for production; use long random values)\n\nStart server (safe local default):\n\nset -a; source .env; set +a\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --auth-token local-openclaw-token \\\n --stats-auth-token local-stats-token\n\nOptional harness activation (runtime in-loop policy controls):\n\n# Observe first (recommended): log decisions, no blocking\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --harness-mode observe\n\n# Enforce mode with limits\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --harness-mode enforce \\\n --harness-budget 1.0 \\\n --harness-max-tool-calls 12 \\\n --harness-max-latency-ms 3500 \\\n --harness-compliance strict\n\nConfigure OpenClaw provider:\n\nbaseUrl: http://:8084/v1 (local default: http://127.0.0.1:8084/v1)\nIf remote: http://:8084/v1 or https:///v1 (TLS/reverse proxy)\napi: openai-completions\nmodel: cascadeflow\napiKey: same value as your --auth-token" }, { "title": "Commands", "body": "/model cflow: default OpenClaw model switch using alias cflow.\n/cascade: optional custom command (if configured in OpenClaw).\n/cascade savings: optional custom subcommand for cost stats.\n/cascade health: optional custom subcommand for service status." }, { "title": "Links", "body": "Full setup + configs: references/clawhub_publish_pack.md\nListing strategy: references/market_positioning.md\nOfficial docs: https://github.com/lemony-ai/cascadeflow/blob/main/docs/guides/openclaw_provider.md\nGitHub repository: https://github.com/lemony-ai/cascadeflow" } ], "body": "CascadeFlow: Cost + Latency Reduction | 17+ Domain-Aware Models + OpenClaw-Native Events\n\nUse CascadeFlow as an OpenClaw provider to lower cost and latency via cascading. Assign up to 17 domain-specific models (for coding, web search, reasoning, and more), including OpenClaw-native event handling, and cascade between them (small model first, verifier when needed). Keep setup minimal, then verify with one health check and one chat call.\n\nWhy Use It\nReduce spend with drafter/verifier cascading.\nRun 17+ domain-aware model assignments (code, reasoning, web-search, and more).\nSupport cascading with streaming and multi-step agent loops.\nHandle OpenClaw-native event/domain signals for smarter model selection.\nSecurity Defaults\nInstall from PyPI and verify package artifact before first run.\nKeep the server bound to localhost by default.\nUse explicit auth tokens for chat and stats endpoints (recommended for production).\nExpose remote access only behind TLS/reverse proxy with strong tokens.\nUse least-privilege provider keys (separate test keys from production keys).\nHow It Works\nOpenClaw sends requests to CascadeFlow through OpenAI-compatible /v1/chat/completions.\nCascadeFlow reads prompt context plus OpenClaw-native event/domain metadata (for example metadata.method, metadata.event, and channel/category hints).\nCascadeFlow selects a domain-aware drafter/verifier pair (small model first).\nIf quality passes threshold, drafter answer is returned (cost/latency advantage).\nIf quality fails threshold, verifier runs and final answer is upgraded.\nThe same cascading behavior is supported for streaming and multi-step agent loops.\nAdvantages\nLower average cost by avoiding verifier calls when not needed.\nLower average latency for simple and medium tasks.\nBetter quality on hard tasks through verifier fallback.\nBetter operational handling through OpenClaw-native event/domain understanding.\nQuick Start\n\nOr ask your OpenClaw agent to set it up for you as an OpenClaw custom provider with OpenClaw-native events and domain understanding.\n\nInstall and verify package source:\npython3 -m venv .venv\nsource .venv/bin/activate\npython -m pip install --upgrade \"cascadeflow[openclaw]>=0.7,<0.8\"\npython -m pip show cascadeflow\npython -m pip download --no-deps \"cascadeflow[openclaw]>=0.7,<0.8\" -d /tmp/cascadeflow_pkg\npython -m pip hash /tmp/cascadeflow_pkg/cascadeflow-*.whl\n\n\nOptional variants:\n\npython -m pip install --upgrade \"cascadeflow[openclaw,anthropic]>=0.7,<0.8\" # Anthropic-only preset\npython -m pip install --upgrade \"cascadeflow[openclaw,openai]>=0.7,<0.8\" # OpenAI-only preset\npython -m pip install --upgrade \"cascadeflow[openclaw,providers]>=0.7,<0.8\" # Mixed preset\n\nPick preset + credentials:\nPresets: examples/configs/anthropic-only.yaml, examples/configs/openai-only.yaml, examples/configs/mixed-anthropic-openai.yaml\nProvider key(s): ANTHROPIC_API_KEY=... and/or OPENAI_API_KEY=... (required based on selected preset)\nService tokens: --auth-token ... and --stats-auth-token ... (recommended for production; use long random values)\nStart server (safe local default):\nset -a; source .env; set +a\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --auth-token local-openclaw-token \\\n --stats-auth-token local-stats-token\n\n\nOptional harness activation (runtime in-loop policy controls):\n\n# Observe first (recommended): log decisions, no blocking\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --harness-mode observe\n\n# Enforce mode with limits\npython3 -m cascadeflow.integrations.openclaw.openai_server \\\n --host 127.0.0.1 --port 8084 \\\n --config examples/configs/anthropic-only.yaml \\\n --harness-mode enforce \\\n --harness-budget 1.0 \\\n --harness-max-tool-calls 12 \\\n --harness-max-latency-ms 3500 \\\n --harness-compliance strict\n\nConfigure OpenClaw provider:\nbaseUrl: http://:8084/v1 (local default: http://127.0.0.1:8084/v1)\nIf remote: http://:8084/v1 or https:///v1 (TLS/reverse proxy)\napi: openai-completions\nmodel: cascadeflow\napiKey: same value as your --auth-token\nCommands\n/model cflow: default OpenClaw model switch using alias cflow.\n/cascade: optional custom command (if configured in OpenClaw).\n/cascade savings: optional custom subcommand for cost stats.\n/cascade health: optional custom subcommand for service status.\nLinks\nFull setup + configs: references/clawhub_publish_pack.md\nListing strategy: references/market_positioning.md\nOfficial docs: https://github.com/lemony-ai/cascadeflow/blob/main/docs/guides/openclaw_provider.md\nGitHub repository: https://github.com/lemony-ai/cascadeflow" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/saschabuehrle/cascadeflow", "publisherUrl": "https://clawhub.ai/saschabuehrle/cascadeflow", "owner": "saschabuehrle", "version": "1.1.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/cascadeflow", "downloadUrl": "https://openagent3.xyz/downloads/cascadeflow", "agentUrl": "https://openagent3.xyz/skills/cascadeflow/agent", "manifestUrl": "https://openagent3.xyz/skills/cascadeflow/agent.json", "briefUrl": "https://openagent3.xyz/skills/cascadeflow/agent.md" } }