Corgi, a helpful {agent, terminal} multiplexer
Hey everyone,Inspired by Herdr, I've built an agent multiplexer that I've been using as my daily driver for a few weeks now.I think I improved on the concept in a few ways, focusing on the ergonomics I always wished I had:I show you what the agents are up to, along with a running feed of their activity. There's also a simple shortcut (F1) to go to the next unread agent.I use multiple accounts, so I've added unified launcher for Codex/Claude Code/Pi. Theres some careful ergonomics there: fast search and resume over sessions, inline usage tracking etc.Many small quality of life improvements to the terminal experience: - Links can be copied with a click, so no need to drag-select over many lines - cmd+v just pastes images (even on SSH) - images have a thumbnail preview. - Built-in CPU/Memory/GPU usage tracking, broken down by workspaceI assume you have access to cheap inference (Luna/Haiku/etc). It just reuses the agents to organize things for you: what is this http link? what is this worktree about? what is each agent doing? It's small but it made my environment feel more cozy.On a personal note, I've been on a frustrating sick leave for a while now. I created Corgi to challenge myself, and see if I can go back. The answer is more mixed than I had hoped, but I am happy with the result and thankful for the experience.I hope you like it! a few friends & myself have been using it for a few weeks and it's been pretty nice. There's still a lot to improve and some rough edges, so feedback would be greatly appreciated.Thank you :)
FL score
out of 100
Verdict
high confidence
Competition
No competitor data yet
Trend
No signal yet
Corgi is a terminal multiplexer that organizes multiple AI agents and improves terminal ergonomics for power users.
The pain
The gap
Build angle
Strengths
- Clear understanding of user pain from personal experience
- Focus on small but meaningful ergonomic improvements
- Integration with multiple AI agents and session persistence
- Feasible for a solo developer to build and maintain
Risks
- Unclear if enough users will pay for this niche tool
- Potential competition from existing terminal multiplexers or AI agent managers
- Limited evidence of strong market demand or growth potential
- Some rough edges and incomplete polish may hinder adoption
Fly Labs Method
Is the pain real, is there a gap, is it the right time, can one person build it.
- Problem clarity
- 70
- Solution gap
- 65
- Willingness to pay
- 60
- Buildability
- 75
The idea addresses a real pain for users juggling multiple AI agents and terminal workflows but the market willingness and clear monetization are uncertain.
Value Equation
Dream outcome and how likely it feels, against the time and effort it costs.
The value proposition is moderate, improving terminal ergonomics and agent management, but the target market size and pricing potential are unclear.
One-Person Business
Curiosity pull, identity fit, and a path from free value to paid for a solo creator.
The concept fits a niche technical audience with some product-market fit potential, though customer acquisition and retention challenges remain.
Viral Frameworks
Hook strength, shareability, and how cheaply it can be tested.
The solution is technically feasible and improves workflow efficiency, but the competitive landscape and user demand need validation.
Builder Lens
Evidence the problem exists, timing, defensibility, and a model that fits on a napkin.
The project shows founder insight and technical skill, but lacks clear evidence of scalable demand or a strong business model.
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 “Corgi, a helpful {agent, terminal} multiplexer”.