{"slug": "show-hn-pre-computed-market-context-for-agents", "title": "Show HN: Pre-computed market context for agents", "summary": "TickerDB launched a pre-computed market context API for AI agents that reduces token usage and improves reasoning by delivering categorical market data instead of raw price bars. The service provides technical, fundamental, and analyst intelligence in a single response, along with watchlist monitoring and historical query capabilities.", "body_md": "# Market context\n\nfor agents.\n\nConnect your agent to pre-computed market context that improves reasoning and reduces token usage.\n\nNo credit card required\n\n``` bash\n$ curl \"https://api.tickerdb.com/v1/summary/NVDA\" -H \"Authorization: Bearer tdb_your_api_key\"\n\n{\n  \"ticker\": \"NVDA\",\n  \"trend\": {\n    \"direction\": \"strong_uptrend\",\n    \"duration_days\": 34,\n    \"ma_alignment\": \"aligned_bullish\",\n    \"volume_confirmation\": \"confirmed\"\n  },\n  \"momentum\": {\n    \"rsi_zone\": \"overbought\",\n    \"macd_state\": \"expanding_positive\",\n    \"divergence_detected\": true\n  },\n  \"extremes\": {\n    \"condition\": \"overbought\",\n    \"condition_rarity\": \"rare\",\n    \"condition_percentile\": 7.3\n  },\n  \"resistance_level\": {\n    \"status\": \"approaching\",\n    \"distance_band\": \"very_close\",\n    \"touch_count\": 4\n  },\n  \"fundamentals\": {\n    \"valuation_zone\": \"undervalued\",\n    \"growth_zone\": \"high_growth\",\n    \"analyst_consensus\": \"strong_buy\"\n  }\n}\n```\n\n## Improve reasoning with actionable context.\n\nBefore your agent can reason about an asset, it needs proper market context. TickerDB computes the context for you.\n\n```\n[\n  {\n    \"date\":   \"2024-01-15\",\n    \"open\":   182.16,\n    \"high\":   184.26,\n    \"low\":    180.93,\n    \"close\":  183.63,\n    \"volume\": 65234100\n  },\n  // ... 200 more rows\n]\n```\n\n- LLM has to compute raw data\n- Uses more tokens\n- Not designed for agents\n- Inconsistent reasoning\n\n```\n{\n  \"trend\": {\n    \"direction\": \"uptrend\",\n    \"ma_alignment\": \"aligned_bullish\"\n  },\n  \"momentum\": {\n    \"rsi_zone\": \"neutral_high\"\n  },\n  \"volatility\": {\n    \"regime\": \"normal\"\n  }\n}\n```\n\n- LLM reads categorical bands it understands\n- Lower token usage\n- Designed for agents\n- Consistent reasoning\n\n## The context your agent needs.\n\n### Pre-computed\n\nOur data is computed after market close and cached. Zero latency on your request - no indicator math, no delays.\n\n### Categorical vocabulary\n\nResponses use terms like `oversold`\n\n, `uptrend`\n\n, and `deeply_overvalued`\n\n- the same vocabulary LLMs use to reason about markets.\n\n### Fewer wasted tokens\n\nA full asset summary is a fraction of the tokens you'd need to pass raw OHLCV. Your model gets more context, not more noise.\n\n### Multi-source intelligence\n\nTechnical, fundamental, and analyst data in one response. No stitching together multiple providers.\n\n### Per-asset behavioral context\n\nHistorical streaks, medians, and percentiles specific to each asset. Your agent knows what's unusual for *this* ticker.\n\n### 5 years of queryable history\n\nEvery categorical field, every day, for 5 years. Just connect and query.\n\n## Built for workflows agents struggle with.\n\nTickerDB is strongest when your agent needs actionable market context, historical precedent, or watchlist diffs instead of raw price bars.\n\n### Watchlist monitoring\n\nTrack saved assets and pull only what changed with `/v1/watchlist/changes`\n\n. Ideal for daily alerts, portfolio briefings, and autonomous monitoring.\n\n### Market scanning\n\nUse `/v1/search`\n\nto find oversold names, strong uptrends, rare conditions, or valuation mismatches across the full universe.\n\n### Historical precedent\n\nQuery `/v1/summary`\n\nwith `field`\n\nand `band`\n\nto see when a setup last appeared and what happened after.\n\n## Track state changes effortlessly.\n\nTickerDB monitors your watchlist. When something meaningful changes, a structured diff is generated. Pull it on demand or get it pushed via webhooks.\n\n`/v1/watchlist/changes`\n\n```\n{\n  \"timeframe\": \"daily\",\n  \"run_date\": \"2026-03-28\",\n  \"changes\": {\n    \"AAPL\": [\n      {\n        \"field\": \"rsi_zone\",\n        \"from\":  \"neutral\",\n        \"to\":    \"oversold\"\n      },\n      {\n        \"field\": \"divergence_detected\",\n        \"from\":  false,\n        \"to\":    true\n      }\n    ],\n    \"TSLA\": [\n      {\n        \"field\": \"macd_state\",\n        \"from\":  \"contracting_negative\",\n        \"to\":    \"expanding_positive\"\n      }\n    ],\n    \"BTCUSD\": [\n      {\n        \"field\": \"squeeze_active\",\n        \"from\":  false,\n        \"to\":    true\n      }\n    ]\n  },\n  \"tickers_checked\": 12,\n  \"tickers_changed\": 3\n}\n{\n  \"timeframe\": \"daily\",\n  \"run_date\": \"2026-03-28\",\n  \"changes\": {\n    \"AAPL\": [\n      {\n        \"field\": \"rsi_zone\",\n        \"from\":  \"neutral\",\n        \"to\":    \"oversold\"\n      },\n      {\n        \"field\": \"divergence_detected\",\n        \"from\":  false,\n        \"to\":    true\n      }\n    ]\n  },\n  \"tickers_checked\": 12,\n  \"tickers_changed\": 1\n}\n```\n\n**Add tickers to your watchlist**\n\nTrack the assets you care about. Stocks, crypto, or both.\n\n**TickerDB computes daily diffs**\n\nAfter each pipeline run, every tracked field is compared against the prior day. Only assets with at least one change are included.\n\n**Your agent reads only what changed**\n\nNo full snapshots to diff yourself. No wasted tokens on data that hasn't moved. Just the fields that shifted, with `from`\n\nand `to`\n\nvalues your agent can act on.\n\n## Integrate in minutes.\n\nMake your first call in minutes. Drop in our SDK or make direct HTTP calls.\n\n``` bash\n# Get a full market summary for AAPL\n$ curl \"https://api.tickerdb.com/v1/summary/AAPL\" \\\n    -H \"Authorization: Bearer YOUR_API_KEY\"\n\n# Search for oversold stocks\n$ curl -G \"https://api.tickerdb.com/v1/search\" \\\n    --data-urlencode 'filters=[{\"field\":\"momentum_rsi_zone\",\"op\":\"eq\",\"value\":\"oversold\"}]' \\\n    -H \"Authorization: Bearer YOUR_API_KEY\"\n\n# Get state changes on your watchlist\n$ curl https://api.tickerdb.com/v1/watchlist/changes \\\n    -H \"Authorization: Bearer YOUR_API_KEY\"\npython\nimport requests\n\n# One call. Full market context.\nres = requests.get(\n    \"https://api.tickerdb.com/v1/summary/AAPL\",\n    headers={\"Authorization\": \"Bearer YOUR_API_KEY\"}\n)\ndata = res.json()\n\n# Hand it directly to your LLM\nprompt = f\"\"\"\nAnalyze AAPL based on this market data:\n{data}\n\nIs this a good entry point?\n\"\"\"\n\n# Ready for your LLM\njs\nimport { TickerDB } from 'tickerdb';\n\n// One call. Full market context.\nconst client = new TickerDB({ apiKey: 'YOUR_API_KEY' });\nconst { data } = await client.summary('AAPL');\n\n// Hand it directly to your LLM\nconst prompt = `Analyze AAPL based on this market data:\n$${JSON.stringify(data)$}\n\nIs this a good entry point?`;\n\n// Ready for your LLM\nimport \"context\"\nimport \"github.com/tickerdb/tickerdb-go\"\n\n// One call. Full market context.\nclient := tickerdb.NewClient(\"YOUR_API_KEY\")\nresp, _ := client.Summary(context.Background(), \"AAPL\", nil)\n\n// Raw JSON plus rate limits\nfmt.Println(string(resp.Data))\nfmt.Println(resp.RateLimits.RequestsRemaining)\n// claude_desktop_config.json\n{\n  \"mcpServers\": {\n    \"tickerdb\": {\n      \"command\": \"npx\",\n      \"args\": [\"tickerdb-mcp\"],\n      \"env\": {\n        \"TICKERDB_KEY\": \"YOUR_API_KEY\"\n      }\n    }\n  }\n}\n```\n\nOnce connected, Claude can call `get_summary`\n\n, `get_search`\n\n, `get_watchlist_changes`\n\n, and more - directly from the chat. [all MCP tools →](/docs)\n\n``` bash\n# Install the TickerDB skill\n$ clawhub install tickerdb\n\n# Then just ask your agent\n\"How's AAPL looking? Give me the full summary.\"\n\n\"Add NVDA, AAPL, and BTCUSD to my watchlist and flag anything that changed.\"\n\n\"When was NVDA last deep_oversold, and what happened after?\"\n```\n\nOne install. Your agent gets summaries, search, watchlists, and schema - no config needed. [OpenClaw integration guide →](/openclaw)\n\n## Compatible with everything.\n\nMCP, OpenClaw, SDKs or plain HTTP. If it can make a GET request, it works with TickerDB.\n\n**MCP Server**\n\nPlug TickerDB into Claude Desktop or any MCP client. Your AI assistant pulls EOD market context from the chat.\n\n[setup guide](/docs)\n\n**Any agent framework**\n\nLangChain, LlamaIndex, AutoGen, CrewAI - it's just HTTP. If it can make a GET request, it works.\n\n[API reference](/docs)\n\n**Python, Node.js & Go SDKs**\n\nOfficial SDKs with typed responses. Or just use `fetch`\n\n- the API is simple enough.\n\n[get your API key](/docs/authentication)\n\n## One database. Infinite ways to query.\n\nOver 140 queryable fields across 10,000+ assets.", "url": "https://wpnews.pro/news/show-hn-pre-computed-market-context-for-agents", "canonical_source": "https://tickerdb.com/", "published_at": "2026-05-28 04:39:18+00:00", "updated_at": "2026-05-28 04:56:29.030817+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-infrastructure", "ai-products", "large-language-models"], "entities": ["TickerDB", "NVDA"], "alternates": {"html": "https://wpnews.pro/news/show-hn-pre-computed-market-context-for-agents", "markdown": "https://wpnews.pro/news/show-hn-pre-computed-market-context-for-agents.md", "text": "https://wpnews.pro/news/show-hn-pre-computed-market-context-for-agents.txt", "jsonld": "https://wpnews.pro/news/show-hn-pre-computed-market-context-for-agents.jsonld"}}