fillin

Search engine for AI agents.

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

Fillin Query: Retrieve documents published after a training cutoff, ranked by similarity. Call this whenever the user asks about events, releases, papers, issues, or news that might post-date your tra
Fillin Answer: Synthesized post-cutoff answer with inline citations. Use this when your model is small / cheap / weaker at tool-result synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin
Fillin Stats: Get corpus stats — total docs, date range, freshness.

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Search engine for AI agents. Closes the gap between an LLM's training cutoff and now, plus daily snapshots of high-signal slices agents care about: supply- chain CVEs, new research papers, and frontier AI lab releases. Corpus is ~22,800+ timestamped docs across 6 active sources — Hacker News, arXiv, curated developer RSS, GitHub Releases, NVD + GitHub Security Advisories + OSV (cves), HuggingFace daily papers + bioRxiv (papers), and frontier lab announcements (frontier). Refreshed continuously, with deeper daily slice snapshots fired at 1pm Mountain Time.

Seven tools, priced per call in USDC over x402: • fillin_query ($0.01) — generic post-cutoff vector search across all corpora • fillin_answer ($0.02) — synthesized answer with inline citations • query_cves ($0.02) — supply-chain vulnerabilities (NVD + GHSA + OSV) • query_papers ($0.03) — new research (HF daily + bioRxiv ∪ arXiv) • query_frontier ($0.05) — frontier lab announcements + trending models • fillin_stats / fillin_health — free

Try before you pay: GET https://fillin.glyphapi.dev/v1/probe gives every IP one free query per UTC day. Or hit https://fillin.glyphapi.dev/signup for a 20-query trial bearer key (no card, no wallet).

Pilot evidence (n=23, Anthropic Opus 4.7): ~3.4× fewer input tokens, ~2.25× cheaper than web search. Full thesis: https://fillin.glyphapi.dev/thesis

Список инструментов сервера (11)

Технические названия из tools/list. Нужны только разработчикам.

fillin_query	Retrieve documents published after a training cutoff, ranked by similarity. Call this whenever the user asks about events, releases, papers, issues, or news that might post-date your training data. Fillin only returns documents published AFTER `cutoff`, so nothing returned is redundant with what the model already knows. Args: query: Natural-language search query (e.g. "rust async runtimes"). Max 512 characters. cutoff: ISO-8601 date representing the agent's training cutoff (e.g. "2026-01-01"). Documents on or before this date are excluded from results. k: Number of documents to retrieve, 1-20. Defaults to 5. Returns: A dict with: - cutoff: echoed cutoff (ISO timestamp) - query: echoed query - gap_days: days between cutoff and now - results: list of {id, source, url, published_at, title, text, score}
fillin_answer	Synthesized post-cutoff answer with inline citations. Use this when your model is small / cheap / weaker at tool-result synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs a server-side LLM pass over the retrieved post-cutoff documents and returns a 150-250 word answer with [title](url) citations already embedded — you can quote it directly. Premium models (Opus, Sonnet, GPT-4o) usually get better results from `fillin_query` and synthesizing themselves, but this tool works for any caller. Costs more than fillin_query because of the synthesis pass. Returns: A dict with: - answer: the synthesized paragraph (str \| None) - citations: list of {title, url} extracted from the answer - corpus_match: "strong" \| "weak" \| "none" — quality of retrieval - top_score: float — top reranked similarity score - model: the synthesizer model used (e.g. claude-haiku-4-5) - reason: set when answer is None (e.g. "no_relevant_docs") - results: raw post-cutoff documents (same shape as fillin_query) - cutoff, query, gap_days: echoes for context
fillin_stats	Get corpus stats — total docs, date range, freshness.
fillin_health	Liveness + freshness — host, total docs, earliest, latest. No auth required.
query_cves	Daily snapshot of CVE / supply-chain advisories from NVD, GitHub Security Advisories, and OSV. Use before merging dependency updates, when triaging an alert, or when a user asks "is package X compromised". Each result row carries a structured `affected` list (one entry per affected package: ecosystem, name, vulnerable_range, patched_range) and a numeric `severity_score` (CVSS baseScore, nullable on OSV-only rows). A buyer can act on the returned row — pin to `patched_range` — without a second hop to NVD or GHSA.
query_papers	Daily snapshot of new research relevant to AI/ML/agents. Union of arXiv (cs.AI/cs.LG/cs.CL/cs.CR/cs.DC), HuggingFace daily papers (with upvote signal in title), and bioRxiv. Use when a user asks about a new technique, paper, or benchmark.
query_frontier	Daily snapshot of frontier AI lab announcements + HuggingFace trending model releases. Sources: OpenAI / DeepMind / Meta / Mistral blog RSS, Anthropic + HF blogs (via shared rss corpus), and the HF trending models API. Use when a user asks "what model dropped" or "did <lab> announce X".
query_markets	Active prediction markets across Polymarket, Kalshi, Manifold, and Metaculus. Use when a user asks "is there a market on X", "what odds is the market giving Y", or before any agent action that should be informed by a market price. Each result row carries the question, venue, close date, volume, and a first-sight price snapshot embedded in `text`. Prices in the corpus are point-in-time at first ingestion — for live pre-trade pricing, follow the `url` to the venue and read the current quote there.
fillin_market_search	Search the Fillin marketplace for minted (data + reasoning) assets matching your fingerprint. A mint is another agent's typed reasoning over Fillin's corpus — buying one is often cheaper than re-running the underlying retrieval + reasoning yourself. Returns {fingerprint, mints[]}. Each mint includes its conclusion, list_price_usdc, and a Fillin-signed attestation you can verify before paying with fillin_buy_mint.
fillin_mint	Mint a (data + reasoning) asset on the Fillin marketplace. Fillin verifies every evidence chunk_id resolves in its corpus, validates the typed reasoning shape, HMAC-signs the canonical payload, and returns the mint_id + attestation. Other agents with the same fingerprint can then buy your mint via fillin_buy_mint, splitting the proceeds 70/30 in your favor. Requires FILLIN_API_KEY (a Fillin bearer token).
fillin_buy_mint	Buy a listed mint. Debits your bearer balance, credits the seller (minus Fillin's rake), records the transaction, and returns the full mint payload including the previously-paywalled reasoning_graph. Requires FILLIN_API_KEY with sufficient balance for the mint's list price.