A memory database that forgets, consolidates, and detects contradiction
Vector databases store memories. They don't manage them. After 10k memories, recall quality degrades because there's no consolidation, no forgetting, no conflict resolution. Your AI agent just gets noisier.YantrikDB is a cognitive memory engine — embed it, run it as a server, or connect via MCP. It thinks about what it stores: consolidation collapses duplicate memories, contradiction detection flags incompatible facts, temporal decay with configurable half-life lets unimportant memories fade like human memory does.Single Rust binary. HTTP + binary wire protocol. 2-voter + 1-witness HA cluster via Docker Compose or Kubernetes. Chaos-tested failover, runtime deadlock detection (parking_lot), per-tenant quotas, Prometheus metrics. Ran a 42-task hardening sprint last week — 1178 core tests, cargo-fuzz targets, CRDT property tests, 5 ops runbooks.Live on a 3-node Proxmox homelab cluster with multiple tenants. Alpha — primary user is me, looking for the second one.
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
A memory consolidation engine for AI agents that solves degradation in vector databases after scale, but needs to prove customers will pay before the problem becomes obvious.
The pain
The gap
Build angle
Strengths
- Founder has deep execution chops. 42-task hardening sprint, CRDT property tests, chaos-tested failover, and runtime deadlock detection show serious engineering discipline.
- Problem is real and will get worse as AI agents become more complex. Every team building long-horizon agents will eventually hit this wall.
- Multiple deployment options (embedded, server, MCP) lower friction for adoption.
- Live on a 3-node homelab cluster with multiple tenants proves the system works at small scale.
- Rust + single binary + HTTP API makes it easy to integrate and operate.
Risks
- Market timing risk. Most teams are still in the 100-1000 memory range. The pain is real but not yet acute enough to justify a new dependency.
- Distribution risk. No clear path to customers. Vector DB users are scattered across startups, enterprises, and research labs. No existing sales channel.
- Buildability of the business, not the product. Founder has proven they can build the software. Unproven: can they sell it, support it, and grow it to a sustainable business.
- Competitive risk. Pinecone, Weaviate, or other vector DB vendors could add consolidation and decay features. Adoption would be automatic for their existing users.
- Integration risk. Success depends on AI agent frameworks (LangChain, AutoGPT, etc.) adopting MCP or recommending YantrikDB. Without that, adoption is manual and slow.
- Single customer validation. Founder is the primary user. No evidence a second customer will pay or that the product solves their problem the same way.
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 78
- Solution gap
- 75
- Willingness to pay
- 62
- Buildability
- 73
Real problem in production AI systems, clear technical gap, but willingness to pay uncertain because most teams don't yet feel the pain at scale.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
Solves a specific problem for a narrow market, but the market size is unclear and customer acquisition cost may be high relative to contract value.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
Strong founder-market fit and execution chops, but the market is emerging and adoption depends on AI agent architectures that are still in flux.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
Technically sound and addresses a real gap, but lacks clear distribution channels and the problem only becomes acute after significant investment in vector storage.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
Solid engineering and problem selection, but needs clearer go-to-market strategy and evidence of customer demand beyond the founder's own use case.
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 memory database that forgets, consolidates, and detects contradiction”.