Mantic.sh – A structural code search engine for AI agents
Author here! Some context: I published this 48 hours ago and it was auto-listed on MCPMarket (the MCP tools directory). Got 700+ organic downloads with zero marketing—developers were actively searching for exactly this solution. The "Git Accelerator" optimization story: Initially used a file walker that took 6.6s on Chromium. Profiling showed 90% was filesystem I/O. The fix: git ls-files returns 480k paths in ~200ms. Added smart heuristics for untracked files (only scan dirs <50k files), bringing total to 0.46s. Why this matters: Agents can't wait 10 seconds for search. Sub-500ms makes…
Mantic.sh – A structural code search engine for AI agents launched on January 6, 2026 with 81 votes, #427 of 14,585 launches that month and more than 95% of that year's launches.
In plain words
Mantic.sh is a structural code search engine designed for AI agents to quickly find specific code patterns and functions across large codebases. It uses Git optimizations to return results in under 500 milliseconds, making it practical for agents that need instant feedback during code exploration. The tool works with Cursor, VS Code, and command-line interfaces, and is best suited for precise queries where code structure matters rather than fuzzy keyword matching.
written from the facts on this page · September 2026
From the sources
A structural code search engine for Al agents. Contribute to marcoaapfortes/Mantic.sh development by creating an account on GitHub.
In the maker’s words, at launch
Author here! Some context: I published this 48 hours ago and it was auto-listed on MCPMarket (the MCP tools directory). Got 700+ organic downloads with zero marketing—developers were actively searching for exactly this solution. The "Git Accelerator" optimization story: Initially used a file walker that took 6.6s on…
Does a similar job
all alternatives →
Semble – Code search for agents that uses 98% fewer tokens than grepMay 2026 · github.com · ▲445Hey 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…
Huzzah – a novel approach to coding with AIAug 2026 · danielvaughn.dev · ▲384Hello everyone. I've been working on this experimental editor called Huzzah. I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself. I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this…
GitHiredDec 2025 · githired.tech · ▲360Hey HN - today I’m launching GitHired. A hiring platform that ranks developers based on what they actually build — not what they claim on a PDF. It’s called GitHired, and here’s the core idea: GitHub > Resumes Instead of trusting “proficient in React” bullet points, we analyze a candidate’s actual GitHub: their real tech stack their most complex projects how active they are what kinds of contributions they make which skills match your job description and yes, we detect fake “green square farming.” Why we built this Because engineering hiring is broken. Resumes are inflated. Activity charts…
SeaGOAT – local, “AI-based” grep for semantic code search2023 · github.com · ▲240local-first semantic code search engine. Contribute to kantord/SeaGOAT development by creating an account on GitHub.
Pu.sh – a full coding-agent harness in 400 lines of shellApr 2026 · pu.dev · ▲92I originally was just messing with pi-autoresearch. Gave it a sample task to build the most portable coding agent. First cut was 6 KB of shell. Great for one-shots, unusable interactively. I was shocked it actually worked. Started building up -- adding features — but with a self-imposed rule: no new dependencies, and sub 500 LOC. This thing had to be truly portable. Just sh, curl, awk. System primitives only. Which means I did some genuinely disgusting things in awk, including JSON parsing and the OpenAI Responses tool loop with reasoning items carried across turns. It's now ~400 lines. In…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
