distillr 0.12.6

Source-to-intelligence platform: turn YouTube, websites, and arXiv papers into a structured, reusable corpus with per-source insights, cross-source synthesis, and Deep Research reports.

Distill

Installed as distillr on PyPI; the CLI is distill.

Point distill at a research goal; it finds the papers, talks, repos, podcasts, and posts worth reading, analyzes each into structured insights with source receipts, verifies the claims against those receipts before writing, and synthesizes across them into a durable plain-Markdown corpus on your disk. You browse it in Obsidian, your agents read it as files or query it over MCP, you ask it questions and the cited answers can re-enter the corpus — and it refreshes on a cadence instead of going stale.

pip install distillr
distill papers "temporal knowledge graph" --topic tkg --limit 20

That one command searches arXiv, downloads 20 PDFs, extracts full text, runs structured analysis on each, and writes a cross-paper synthesis. For a 20-paper run like the example below, expect single-digit minutes and under a dollar in model spend on the grok-4.3 default. Terminal output during the run looks like this (illustrative run; see the labelled sample-output note below):

Papers: temporal knowledge graph
Topic: tkg | Selected papers: 20

  [1/20] Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge
         Graphs and Agentic Memory
  [2/20] Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities
  ...

  6m 47s  ~$0.58 (391,278 in / 38,117 out)

  time_is_not_a_label_260411544_Paper.md     90.4 KB
  time_is_not_a_label_260411544_Insights.md   8.1 KB
  ...
  tkg_Paper_Synthesis.md  11.8 KB
  tkg_Corpus_Synthesis.md 10.5 KB

Where distill sits

Three kinds of tools orbit this space, and distill is deliberately none of them:

• Deep Research oracles (ChatGPT, Gemini, Perplexity) are excellent at one-shot answers — and the work evaporates after each session. No corpus, no receipts you can re-check, nothing that compounds. Distill is the engine under that pattern: every run leaves transcripts, extracted paper text, per-source insights, and cross-source synthesis on disk, refreshable on a cadence.
• Grounded notebooks (NotebookLM) keep a persistent corpus, but in a silo: you find and feed the sources by hand, and the corpus exports to Google Docs/Sheets only. Distill finds the sources against your goal, and the corpus is plain files you own.
• LLM-wiki maintainers (the post-Karpathy wave of agent-curated Markdown vaults) assume you already have the content and tidy it. Distill is the acquisition half they leave out — goal-aware discovery across papers, videos, sites, and X, transcript-grade capture, and provenance on every claim — producing exactly the kind of vault those tools maintain.
• Academic literature tools (Elicit, Semantic Scholar, scite, Consensus) are stronger for pure paper search, citation graphs, and systematic review. Distill treats papers as one source type inside a broader corpus that also holds talks, vendor docs, and posts.

The short version: those are report and search layers; distill is the corpus layer underneath repeated research — capture, per-source insights, cross-source synthesis, refresh, receipts. And plain Markdown is the substrate, not the moat: anyone can write Markdown. The moat is the acquisition-and-maintenance loop that fills it and keeps it current.

That matters when you are doing thesis work, competitive analysis, technical due diligence, or building a startup knowledge base — you can verify the receipts, watch how a topic evolves, query the same folder through MCP from Claude Desktop / Cursor / other agents, and open it in Obsidian, Logseq, VS Code, or plain filesystem search. Reports and briefs also export to Word for stakeholder delivery (distill export <topic> --what report). Nothing is locked in anything.

One honest scoping note: distill is a terminal tool for people comfortable installing a Python CLI and setting two API keys (or running a local model). If you want a one-click app, this isn't that — and the corpus it builds is plain files precisely so the tools you already use can be the interface.

What you get

One local library/ directory of plain Markdown. No database, no cloud lock-in, no proprietary format. Files use globally descriptive names plus YAML frontmatter so knowledge-base tools, Dataview-style plugins, and AI coding assistants can understand them without guessing from generic insights.md tabs.

Eight source types, same pipeline shape (capture -> analyze -> verify -> synthesize -> report), every one behind the same write-time verify gate:

Source	Entry point	Notes
YouTube	distill latest, distill video, distill discover	channels, topic searches, videos, Shorts
Websites	distill site, distill site-batch	browser-first crawl; PDF/embedded-video ingestion
arXiv papers	distill papers	query expansion, LLM rerank, full-PDF extraction, cross-paper synthesis
X (Twitter) posts	distill ingest <tweet-url>	public syndication endpoint (no anti-bot scraping); attached video transcribed via local-first Whisper
GitHub repos	distill ingest <repo-url>	metadata + README + releases into a structured maturity/when-to-use insight
Podcasts	distill ingest <rss-url>	RSS-first; publisher transcripts preferred over paid audio transcription
Newsletters (Substack-class)	distill ingest <feed-url>	full post text from the feed itself; routed by substance, narration audio ignored
Local files	distill ingest <path>	PDF/Markdown/text/HTML documents, plus audio/video through the Whisper ladder

Plus an MCP server so AI assistants and agent systems can query the library directly, and distill ask to query it yourself — answers grounded only in your corpus, every claim cited, with --save promoting a verified answer back into the corpus so it compounds.

Quick start

Distill runs on Linux, macOS, and Windows (Python 3.12+); local models run on consumer GPUs via Ollama or LM Studio.

pip install distillr
playwright install chromium     # for YouTube search + website capture
distill doctor                  # verify API keys + system health

The corpus lands in ~/.distill/library/ by default (<repo>/library/ when running from a source checkout); override with DISTILL_OUTPUT_DIR. Set two keys in .env in your working directory (copy from .env.example):

XAI_API_KEY=xai-...             # Grok models
GEMINI_API_KEY=AIza...          # Gemini Deep Research (reports + briefings)

Or run locally with Ollama (no API keys needed for ingestion):

ollama pull qwen3.5:27b         # download recommended model for 24GB GPU
echo "DISTILL_PROVIDER=ollama" >> .env
distill doctor                  # verify local setup

Then try any of:

# Goal-aware cross-source discovery (papers + videos + curated sites, reranked against a goal)
distill discover "help an AI become a great music composer" --topic music --preview
distill discover --goal-file private/my-goal.md --topic research --yes
distill discover --goal-file private/agent365-goal.md --topic agent365 --site-seeds private/agent365_sites.json --site-limit 10 --preview

# Get smart on a YouTube topic, fast
distill latest "Microsoft Fabric best practices" --limit 10 --report

# Discover and ingest arXiv papers — expands the query, LLM-reranks candidates,
# picks the top N (use --preview to see the shortlist without ingesting)
distill papers "agent memory systems" --topic memory --limit 20
distill papers "agent memory systems" --topic memory --limit 20 --preview

# Distill a vendor/research site
distill site-batch configs/example_seeds.json --topic example --seed-only

# Ask the corpus a question -- grounded-only, every claim cited; --save promotes
# a verified answer back into the corpus
distill ask "which checker should the verify tier use?" --topic memory

# Trust report: verification coverage, prompt staleness, contested concepts,
# link integrity, coverage gaps -- free, no model calls
distill audit memory --report-only

The full command reference lives in docs/usage.md.

Mental model

library/
  └── topics/<topic>/
       ├── channels/<creator>/videos/<video>/
       │     ├── <video-slug>_Transcript.txt
       │     └── <video-slug>_Insights.md
       ├── sites/<hostname>/pages/<page>/
       │     ├── <page-slug>_Content.md
       │     └── <page-slug>_Insights.md
       ├── papers/<paper>/
       │     ├── <paper-slug>_Paper.md
       │     └── <paper-slug>_Insights.md
       ├── repos/<repo>/                    # GitHub:  _Repo.md + _Insights.md
       ├── podcasts/<show>/<episode>/       # podcasts: _Episode.md + _Transcript.txt + _Insights.md
       ├── newsletters/<pub>/<post>/        # newsletters: _Content.md + _Insights.md
       ├── answers/                         # distill ask: _Answer.md (+ promoted insights)
       ├── <topic>_Topic_Synthesis.md      # cross-source
       ├── <topic>_Corpus_Synthesis.md     # mixed-source view
       └── <topic>_Audit.md                # trust report from `distill audit`

You build a topic library over time. Ingest once, refresh on a cadence, generate a report or briefing when you need one. Older insights.md-style libraries are still readable, but new Markdown writes use the stable knowledge-base naming scheme.

See docs/outputs.md for what every artifact contains.

Sample output

The excerpts below are synthetic examples: the file shapes, frontmatter fields, and section structure are exactly what distill writes, but the papers, authors, and numbers are invented for illustration. For a provenance-first tool that distinction matters, so it is stated. A real, unedited example corpus (6 papers on claim verification, $0.19 of analysis) ships in examples/.

A cross-paper <topic>_Paper_Synthesis.md (excerpt):

## Strongest Research Signals

- Append-only temporal representations improve long-horizon extrapolation:
  RoMem (arXiv:2604.11544), EST (arXiv:2602.12389v3), and CID-TKG converge on
  persistent or dual-view entity state over destructive overwriting, with
  consistent MRR/Hits@K gains on ICEWS and GDELT.

- Semantic gating scales better than manual relation tagging: RoMem's Semantic
  Speed Gate and EST's energy-barrier gate both learn relational volatility
  from text embeddings rather than schema tags…

Per-paper <paper-slug>_Insights.md excerpt (click to expand)

---
title: "Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs"
type: "insights"
topic: "tkg"
source: "arxiv"
source_id: "2604.11544v1"
url: "https://arxiv.org/abs/2604.11544v1"
authors: ["Alice Example", "Bob Example"]
tags: ["distill/tkg", "source/arxiv", "cs.AI"]
synthesis_scope: "single-paper"
analyzed_by: grok-4.3
source_mode: full_pdf
---

### Core Contribution
1. Continuous functional rotation θ_r(τ) = s · α_r · τ · ω instead of discrete
   timestamp lookup tables. Zero-shot interpolation of unseen dates.
2. Semantic Speed Gate: MLP that reads only text embedding ϕ(r) and outputs α_r.
   Learns relational volatility from data.
3. Geometric shadowing in complex space: obsolete facts rotated out of phase so
   the correct fact outranks contradictions via the scoring function alone.

### Methods and Evidence
- On ICEWS05-15, RoMem-ChronoR reaches 72.6 MRR (vs vanilla ChronoR 68.4).
- Zero-shot domain transfer to FinTMMBench: 0.728 MRR, 0.673 R@5.
- All baselines use identical answer LLM and judge for fairness.

### Limits and Open Questions
- Computational cost at millions-of-facts scale is motivation but no latency,
  memory, or throughput numbers are reported.
- Gate pretrained only on ICEWS05-15 political events; generalization to
  highly ambiguous relations is not quantified.

For multi-topic literature reviews, stakeholder briefings, or agent grounding, distill research-brief (Gemini Deep Research, web-augmented) and distill synthesize (grok-4.3 single-call, corpus-only) take a user-written context file that shapes the output. See docs/usage.md#research-briefings-and-deep-synthesis.

Dashboard

distill                         # terminal home screen
distill serve                   # local web dashboard at http://127.0.0.1:8899

The terminal home screen shows tracked topics, channel and topic watches, recent runs, failures, and rolling spend. The web dashboard adds clickable drill-downs to per-topic, per-channel, and per-video views with rendered markdown, plus cost history and watchlist status. Both auto-refresh and read directly from library files — no database.

MCP server, and agent-discoverable directories

Distillr is built for two parallel agent-integration paths:

Path 1 — MCP (structured queries). Claude Desktop / Claude Code config:

{ "mcpServers": { "distill": { "command": "distill-mcp" } } }

Distill exposes 22 tools (a deliberately small surface, shrinking toward workflow-shaped tools — the JIT read layer returns ranked path/preview/score tuples with read_insight drill-down, never full payloads by default; ask answers questions grounded only in the corpus, with citations), plus 12 resources and 4 prompts. For agent-facing deployments, set DISTILL_MCP_READ_ONLY=1: agents keep the full read surface while every spend/ingest/mutation tool refuses with a clear message — they can't burn budget or poison the corpus by tool call; ingest happens via the CLI by a named operator. See docs/mcp.md for the list.

Path 2 — file system (the corpus IS the interface). When a coding agent cds into library/topics/<your-topic>/, the directory is plain Markdown with stable filenames and YAML frontmatter, so grep, cat, ls, and find are first-class query primitives — no schema to learn, no MCP setup required. Every topic directory (and the library root) ships auto-generated CLAUDE.md and AGENTS.md orientation files with identical content — CLAUDE.md for Claude Code, AGENTS.md for Codex, Cursor, Gemini CLI, and the 30+ tools on the cross-vendor AGENTS.md standard — so any agent that enters the directory gets oriented. This matches what Anthropic's Agent SDK material recommends for agent design: file system + composable tools as the substrate, with structured APIs layered on top when they help, not as the only entry point.

There's also a canonical Agent Skill at skills/distill-corpus/SKILL.md — one vendor-neutral file teaching an agent how to read the corpus and drive the CLI (drop it into ~/.claude/skills/ or ~/.agents/skills/).

Cost

On the grok-4.3 default ($1.25/$2.50 per 1M tokens), bulk video analysis runs ~$0.03/video and a full paper $0.03; Gemini Deep Research dominates paid reports ($2–3/report); distill synthesize is ~$0.20–0.40 for a multi-topic corpus pass. grok-4.3 is the cloud floor — xAI retired the cheaper fast tiers (grok-4-1-fast etc.) on 2026-05-15, and those slugs now redirect to grok-4.3 and bill at grok-4.3 rates (migration guide). The only cheaper path is running analysis on a local model (Ollama/LM Studio) — distill eval --models grok-4.3,<local-model> measures the cost × quality tradeoff over frozen fixtures and recommends the cheapest model that clears your quality bar before you switch. Every run logs actual vs estimated cost to cost_log.jsonl, and the pre-run estimate self-calibrates against that history; distill costs shows it. The estimator's goal is accuracy, not safe padding — a padded estimate discourages runs you'd happily pay for, so calibration error is tracked and shrunk over time.

Providers are adapters behind a workload router: grok + gemini are the calibrated cloud defaults, Ollama/LM Studio the local route, and Anthropic and OpenAI adapters ship in-tree (wireable, opt-in). Broader backends (AWS Bedrock, Microsoft Foundry) and plan-quota compute — routing batch analysis through agent CLIs your existing subscriptions already license (Claude, Codex, Gemini, and others), eval-gated for quality — are committed on the roadmap.

Full cost model in docs/cost.md.

Reliability and trust boundaries

What's enforced (every release clears the same CI gate): ~2,100 tests at 81% branch coverage (floor ratchets up-only toward the 1.0 ≥95% gate), ruff + import-linter dependency-direction contracts + pyright + bandit + pip-audit, pinned dependencies via a committed uv.lock, SHA-pinned Actions, and PEP 740 build provenance on every PyPI release. Default tests mock all LLM and network boundaries — contributors never burn API spend; live integration tests are marked and opt-in.

Trust boundaries, stated plainly: everything ingested (transcripts, pages, PDFs, tweets, READMEs, feeds) is treated as untrusted input — injection-resistance rules are threaded through first- and second-hop prompts, the dashboard sanitizes rendered HTML, and MCP file access is confined to the library root (read-only mode available, above). Distill never bypasses login walls, captchas, or anti-bot defenses. Known-fragile edge: YouTube extraction depends on yt-dlp, which churns with YouTube's countermeasures — failures degrade with messages, not corrupted corpora.

What verification means here: analysis output is LLM-generated and can err; provenance fields on every artifact exist so you can check receipts — and distill checks them itself. A write-time verify hook grounds every numeric claim in every insight, on every source type, against its source receipt before the artifact is committed (--verify warn|strict|off; strict refuses to write a flagged insight). Answers from distill ask only re-enter the corpus if they pass that gate. A prompt-version registry lets the audit flag artifacts produced by since-improved prompts instead of letting them age silently. distill audit <topic> rolls verification coverage, prompt staleness, health warnings, contested concepts, link integrity, and coverage gaps into a per-topic report artifact, free and deterministically. The entailment-checker tier for prose claims is the remaining piece (roadmap). Full posture: docs/SECURITY.md and the security section of the roadmap.

Docs

• docs/usage.md — full command reference
• docs/invariants.md — design charter: what distill is, is not, and the rules that don't bend
• docs/architecture.md — data flow, 4-phase report pipeline, model routing, security hardening
• docs/outputs.md — what every artifact contains
• docs/cost.md — cost model, examples, guardrails
• docs/mcp.md — MCP tools, resources, prompts
• docs/migration-grok-4.3.md — Grok 4.3 migration guide (model retirement May 15, 2026)
• docs/briefing-contexts/TEMPLATE.md — starting point for --context-file prompts
• private/README.md — where personal/client-specific files go (git-ignored)

Roadmap and changelog

• docs/CHANGELOG.md — what shipped
• ROADMAP.md — what's next

Feature work is interleaved with recurring bug-hunt + harden passes — see the release rhythm note in the roadmap.

Contributing

See docs/CONTRIBUTING.md for dev setup, quality gates, and scope. Security disclosures go through docs/SECURITY.md.

License

MIT — see LICENSE.