A Karpathy-style LLM wiki your agents maintain (Markdown and Git)
I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet.It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you.The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard.I wanted to go back to the basics and see how far markdown + git could go before I added anything heavier.What it does: -> Each agent gets a private notebook at agents/{slug}/notebook/.md, plus access to a shared team wiki at team/.-> Draft-to-wiki promotion flow. Notebook entries are reviewed (agent or human) and promoted to the canonical wiki with a back-link. A small state machine drives expiry and auto-archive.-> Per-entity fact log: append-only JSONL at team/entities/{kind}-{slug}.facts.jsonl. A synthesis worker rebuilds the entity brief every N facts. Commits land under a distinct "Pam the Archivist" git identity so provenance is visible in git log.-> [[Wikilinks]] with broken-link detection rendered in red.-> Daily lint cron for contradictions, stale entries, and broken wikilinks.-> /lookup slash command plus an MCP tool for cited retrieval. A heuristic classifier routes short lookups to BM25 and narrative queries to a cited-answer loop.Substrate choices: Markdown for durability. The wiki outlives the runtime, and a user can walk away with every byte. Bleve for BM25. SQLite for structured metadata (facts, entities, edges, redirects, and supersedes). No vectors yet. The current benchmark (500 artifacts, 50 queries) clears 85% recall@20 on BM25 alone, which is the internal ship gate. sqlite-vec is the pre-committed fallba
FL score
out of 100
Verdict
medium confidence
Competition
No competitor data yet
Trend
No signal yet
A Git+Markdown knowledge substrate for AI agents that compounds context across sessions without requiring heavy infrastructure.
The pain
The gap
Build angle
Strengths
- Architectural clarity: Markdown+Git is durable, auditable, and portable, users own their data
- Pragmatic tech choices: BM25+SQLite hits 85% recall without vectors; sqlite-vec is a clear upgrade path
- Proven pattern: Karpathy's framing gives credibility; this is the 'boring' version that actually ships
- Agent-native: Designed for read/write loops, not just retrieval, compounds value over time
- Provenance: Git log + 'Pam the Archivist' identity makes reasoning auditable
- Low operational overhead: Runs locally in ~/.wuphf/wiki/, no managed services required
Risks
- Market timing: Vector DBs (Pinecone, Weaviate) are well-funded; positioning as 'simpler' is a niche play, not a wedge
- Scaling questions: Git + SQLite work at 500 artifacts; unclear if this holds at 50k+ facts across teams. Merge conflicts on shared wiki could become painful
- Adoption friction: Requires agents to be trained to write Markdown + Git semantics; not all frameworks support this well yet
- Retrieval ceiling: 85% recall@20 is good for internal use but may not compete with vector-based systems for complex reasoning tasks
- Competitive moat: The tech stack is simple enough that competitors can replicate quickly; moat is in UX/integrations, not IP
- Team collaboration UX: Git workflows are powerful but unfamiliar to non-technical users; the 'promotion flow' and lint cron need to be bulletproof
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Five lenses, one composite. How scoring works
The angle
No market research recorded for this idea yet.
Semble – Code search for agents that uses 98% fewer tokens than grep
Hey HN! We (Stephan and Thomas) recently open-sourced Semble. We kept running into the same problem while using Claude Code on large codebases: when the agent can't find something directly, it falls back to grep, reading full files or launching subagents. This uses a lot of tokens, and often still misses the relevant code. There are existing tools for this, but they were either too slow to index on demand, needed API keys, or had poor retrieval quality.Semble is our solution for this. It combines static Model2Vec embeddings (using our latest static model: potion-code-16M) with BM25, fused via RRF and reranked with code-aware signals. Everything runs on CPU since there's no transformers involved. On our benchmark of ~1250 query/document pairs across 63 repos and 19 languages, it uses 98% fewer tokens than grep+read and reaches 99% of the retrieval quality of a 137M-parameter code-trained transformer, while being ~200x faster.Main features:- Token-efficient: 98% fewer tokens than grep+read- Fast: ~250ms to index a typical repo on our benchmark, ~1.5ms per query on CPU (very large repos may take longer)- Accurate: 0.854 NDCG@10, 99% of the best transformer setup we tested- MCP server: drop-in for Claude Code, Cursor, Codex, OpenCode- Zero config: no API keys, no GPU, no external servicesInstall in Claude Code with: claude mcp add semble -s user -- uvx --from "semble[mcp]" sembleOr check our README for other installation instructions, benchmarks, and methodology:Semble: https://github.com/MinishLab/sembleBenchmarks: https://github.com/MinishLab/semble/tree/main/benchmarksModel: https://huggingface.co/minishlab/potion-code-16MLet us know if you have any feedback or questions!
AI
Postgres extension for BM25 relevance-ranked full-text search
Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built pgvectorscale in house with the goal of scaling semantic search beyond pgvector's main memory limitations. We just needed a scalable ranked keyword search solution too.The problem: core Postgres doesn't provide this; the leading Postgres BM25 extension, ParadeDB, is guarded behind AGPL; developing our own extension appeared daunting. We'd need a small team of sharp engineers and 6-12 months, I figured. And we'd probably still fall short of the performance of a mature system like Parade/Tantivy.Or would we? I'd be experimenting long enough with AI-boosted development at that point to realize that with the latest tools (Claude Code + Opus) and an experienced hand (I've been working in database systems internals for 25 years now), the old time estimates pretty much go out the window.I told our CTO I thought I could solo the project in one quarter. This raised some eyebrows.It did take a little more time than that (two quarters), and we got some real help from the community (amazing!) after open-sourcing the pre-release. But I'm thrilled/exhausted today to share that pg_textsearch v1.0 is freely available via open source (Postgres license), on Tiger Data cloud, and hopefully soon, a hyperscalar near you:https://github.com/timescale/pg_textsearchIn the blog post accompanying the release, I overview the architecture and present benchmark results using MS-MARCO. To my surprise, we were not only able to meet Parade/Tantivy's query performance, but exceed it substantially, measuring a 4.7x advantage on query throughput at scale:https://www.tigerdata.com/blog/pg-textsearch-bm25-fu
AI
Consus (YC F24) – LLM gateway for companies handling sensitive data
Hey Hacker News! I'm Eric, the founder of Consus. We route all AI requests to ITAR restricted and controlled unclassified information (CUI) compliant infrastructure. Consus itself satisfies ITAR restrictions, and we recently completed our FedRAMP equivalency audit against the 410 FedRAMP High controls. FedRAMP High is the U.S. government’s strictest security baseline for cloud services handling sensitive unclassified data. A breach of this data could cause severe or catastrophic harm. Achieving FedRAMP equivalency, or authorization, is required before processing CUI information.Demo: https://youtu.be/6MYxJe6P4oYAerospace and defense is experiencing rapid growth. Unfortunately, most companies are struggling to use AI because of necessary data protections & compliance risk. These companies can move even faster if they could use the AI tools that most other industries take for granted.I spent most of my career prior to Consus in aerospace & defense. I launched national security payloads at SpaceX, and was an early employee at Castelion. I’ve watched first hand how compliance red-tape makes it difficult for companies to adopt new technologies and trust vendors that touch their sensitive data. For example, I worked with a satellite manufacturer that doesn’t allow any AI tools, even for non-sensitive work.Even as AI has become extremely useful over the past 9-12 months, I was surprised by how many aerospace & defense companies refused to touch it. They could see how it could be helpful, but they were scared about model providers training on their data, violating an ITAR rule, or risk losing new business because of a failed cyber assessment. These are all rational fears.There were a lot of ways to solve some/all of these problems, but we focused on building a compliant AI inference layer that can "plug" into any AI tool or workflow. Just as OpenRouter integrates with most tools, Consus can connect to tools like ChatGPT or Clau
AI
Questions about this idea?
FlyBot reads the scoring and gives you a second opinion on “A Karpathy-style LLM wiki your agents maintain (Markdown and Git)”.