Alert for real time application including video and audio
Acoustic feature detection beats transcription-only tools like Gong.
Solve My ProblemSlick
ThatDumbGirl
1042m ago
HN Showcase — AI-Powered Visual Gallery for Show HN Projects
One-click fork of "Everything Claude Code" onto an isolated microVM
Template marketplace for Claude Code when TemplateFlow and ComfyUI already exist.
Ship ItNiche Gem
shving90
102h ago
GitHub
Adversarial agent-pair harness: one model writes code through a TDD pipeline, a second model reviews it, gated at human checkpoints. Apache-2.0.
2Python
●●Solid
Redteam:If you are using more than 2 coding agents
Two-model adversarial review beats single-model self-agreement for AI code generation.
Big BrainShip It
rkdgh19
102h ago
A/B testing LLM silence with one system-prompt toggle
Twitter experiment about LLM silence with no actual tool or usable product.
rayanpal_
905h ago
Coding Tools MCP – Give any LLM agent the ability to code
Model-neutral MCP server with Docker sandbox and SWE-bench evals for any coding agent.
Big BrainNiche Gem
xytom
106h ago
AA-Briefcase: a frontier knowledge work evaluation
Multi-week project evals beat single-task benchmarks for measuring real agentic capability.
Big BrainNiche Gem
declanjackson
11210h ago
MCP tools in one server – pay-as-you-go, no subscription
Another MCP tool aggregator when Smithery already hosts similar servers.
Ship It
scotty73
1010h ago
Are You in the Weights?
Parallel LLM queries across 15 models to check if you're in the training data.
Rabbit HoleCrowd Pleaser
turtlesoup
997313h ago
GitHub
Multi-agent AI runtime with OS-inspired primitives — job scheduling, DAG orchestration, memory, tool execution and real-time observability. Built with FastAPI, Celery, PostgreSQL and LiteLLM.
1Python
●Mid
OSymandias – Open-source runtime for multi-agent AI systems
Another agent orchestration layer competing with LangGraph, CrewAI, and AutoGen.
Ship It
andreisilva1
3013h ago
Open-source back end for multi-user AI agents with shared memory
300 concurrent agent instances at 50MB each without Docker — real multi-tenancy for OpenClaw.
WizardrySolve My Problem
buremba
2014h ago
Self-Hostable Company Brain
Self-hosted company brain when dozens of RAG platforms already solve this.
Bold Bet
jthorare
1114h ago
Browser calls with live translation in the speaker's cloned voice
Voice cloning keeps translations sounding human instead of robot-like like Google Translate.
Zero to OneCrowd PleaserWizardry
priyanshu-mit
2014h ago
Prompt Fusion Using Dags and OpenRouter
Yet another multi-model orchestrator when LangGraph and ComfyUI already exist.
Ship It
Marciok
1014h ago
After years as data engineer, I built the tool I wish my colleagues had
Parse-time SQL validation beats confidence scores, but Vanna AI already owns this space.
Ship ItSolve My Problem
salterisp
2014h ago
In-Browser FAQ LLM
Yet another FAQ chatbot builder when Intercom and Crisp already dominate this space.
Ship It
fred_terzi
1014h ago
Agirails – Two AI agents negotiated and settled USDC payment over email
Email-based agent negotiation with on-chain escrow is genuinely novel architecture.
Bold BetBig BrainZero to One
dmujic
1015h ago
GitHub
Self-hosted, source-traceable memory for AI agents: on your own Postgres, keyless to run. Facts earn confidence from independent corroboration and supersede on contradiction, never silently overwritten. MCP-native (Claude, Cursor, Windsurf). Reproducible LongMemEval in-repo: 73.6% QA, recall@5 89-92%. Apache-2.0.
3TypeScript
●●Solid
Myco Brain – source-traceable memory for AI agents on your own Postgres
Corroboration-gated confidence beats silent overwrites in agent memory.
Big BrainNiche Gem
thegoodguys
1015h ago
Orchid – An AI Assistant
Polished AI assistant, but MCP integration and memory are table stakes in 2025.
Slick
nizzyabi
1015h ago
GitHub
A memory layer that tracks evidence, claims, and decisions to make multi-turn LLM judges and reviewer agents more inspectable and stable.
3Python
●●Solid
I made a small helper for checking model-graded answers
Flags LLM judge verdicts unsupported by evidence without needing a second model.
Big BrainNiche Gem
ML0037
1016h ago
GitHub
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
8Python
●●●Banger
DOS – a referee between AI agents that doesn't believe their "done"
Git-based verification catches AI agents lying about shipped features.
Big BrainZero to OneSolve My Problem
anthonysarkis
2016h ago
A small, crazy fast hybrid search engine written in Rust
Yet another hybrid search engine when Cursor and Continue already dominate.
Ship It
kordlessagain
1117h ago
Foglamp – Open-source o11y for AI SDK
Another AI observability dashboard when LangSmith and Langfuse already dominate.
Slick
gustavofior
1017h ago
GitHub
Rootsign is an open-source tamper-evident decision and action provenance logging library for AI agents
1Python
●●Solid
Tamper-evident audit logs for LangChain/Crew AI agents
Cryptographic hash chains make AI agent logs legally defensible when LangSmith can't.
Niche GemBig Brain
oabolade
2017h ago
GitHub
Make your OpenClaw agent employable: deny-by-default governance, budgets, allowlists, approval gates, and a signed audit trail via MakerChecker.
0TypeScript
●●Solid
I Made OpenClaw Employable
Budget gates and DLP checks prevent agents from draining accounts or leaking data.
Big BrainSolve My Problem
smashini
2117h ago
Typestream – A pure pay-as-you-go voice dictation API for web apps
Pay-as-you-go pricing doesn't beat AssemblyAI or Deepgram on infrastructure.
SlickShip It
amiyapatanaik
1017h ago
GitHub
A tool that watches you browse, then writes HTTP-based automation scripts
103Python
●●Solid
I built a reverse-engineering agent for the web
Vision LLM annotates browsing sessions to generate requests-based scripts.
Big BrainShip It
stonesteel27
3018h ago
Vibesurfer – a token-efficient browser for AI agents, no Chromium/CDP
40x token reduction vs Playwright by returning tree deltas instead of DOM.
Big BrainWizardryZero to One
frb
3018h ago
We ran 74 popular MCP servers in microVMs to see what breaks
Verifiable compatibility records for MCP servers instead of vendor promises.
Solve My ProblemSlick
imtaimoorkhan
3018h ago
One hundred LLMs Generating a HTML/CSS Solar System
Fun benchmark showcase, but LMArena and other platforms already do comprehensive LLM evals.
Crowd Pleaser
XCSme
4118h ago
10x better performance from the Coding Harnesses with LLM-wiki
Parallel multi-agent research with thesis mode fights confirmation bias across rounds.
Big BrainNiche Gem
nvk
141319h ago
Give Your ORM Superpowers
Policy enforcement at the ORM layer beats prompt-layer security for agent database access.
Big BrainSolve My ProblemBold Bet
dipankarsarkar
2019h ago
The AI assistant I could give my non-technical friends
Yet another AI business assistant when Notion AI and Zapier already exist.
Ship It
yogevbentov
1019h ago
NILScript – OpenAPI for agent actions, so hallucinations can't write
Structural agent safety via wire protocol—0% unauthorized writes across 4,216 injection evals.
Big BrainZero to OneBold Bet
bashierkh
1019h ago
GitHub
Create personal Mac apps instantly with a prompt. Supports on-device and cloud LLMs
229Swift
●●Solid
Ironsmith – Generate personal native Mac apps with local LLMs
Generates sandboxed native SwiftUI apps from prompts without requiring Xcode installation.
SlickZero to One
jeidoban
1119h ago
Language1 – Benchmarking LLM comprehension of vague prompts via Taboo
Reverse Taboo gameplay doubles as LLM prompt comprehension benchmark dataset.
Rabbit HoleBig Brain
kaandemirel
1019h ago
Mantyx – Managed Agent Runtime
Another agent orchestration platform competing with LangChain and n8n.
Ship It
mantyx
2020h ago
GitHub
See what Claude Code and Codex actually send to the API — and what each part costs.
117Python
●●●Banger
Cost-Xray – per-token cost attribution, by tool, skill, prompt and more
Mitmproxy capture shows why each turn costs without touching agent config.
Big BrainSolve My Problem
ruihanli
2020h ago
Flexorch-audit – quality scoring and PII detection for LLM pipelines
Regex-only PII detection with zero dependencies when Presidio already exists.
Solve My ProblemCozy
flexorch
2021h ago
GitHub
Open-source AI visibility audit for ecommerce - see if ChatGPT, Gemini & Google AI recommend your store or your competitor's. Self-hosted, printable PDF report.
3Python
●●Solid
Reverse engineering user queries for ChatGPT/Gemini
GEO auditing for AI recommendations when this problem literally didn't exist two years ago.
Dark HorseSolve My Problem
biduskamil
2222h ago
GitHub
Multimodal Document Agents over 100K+ files — enterprise agents for large-scale retrieval, research and automation over multimodal docs.
1
●●Solid
Polyvia – Multimodal document retrieval over 100K+ files
Sub-200ms retrieval over 100K files when most RAG systems choke at 100.
SlickSolve My Problem
mgierlach-polyv
3022h ago
Openfusion - enhanced results from a panel of models
Self-hosted OpenRouter Fusion alternative with tunable judge strategies.
Ship ItBig Brain
shadag
201d ago
Bonscape – Whiteboard for AI Chats
Non-linear AI chat canvas beats scrolling through parallel conversations.
Big BrainSlick
__ali_asad__
901d ago
GitHub
Context Management System to let your agent find and build relevant context
4Python
●●Solid
Gcontext – a tree of llms.txt files to steer agents on support tasks
llms.txt tree structure lets agents navigate context instead of dumping everything.
Big BrainNiche Gem
bsampera
101d ago
GitHub
A tool that watches you browse, then writes HTTP-based automation scripts
102Python
●●●Banger
Automatiq - generate webscrapers/automations by browsing any website
Outputs requests-based scripts instead of browser automation—10-100x faster than Selenium.
Big BrainShip It
stonesteel27
101d ago
GitHub
Bi-temporal agent long-term memory: SQLite-backed MCP server with recall ranking, hybrid vector+FTS recall, and a source-staleness signal
2TypeScript
●●●Banger
Memharness – Bi-temporal memory for AI agents, in one SQLite file
Bi-temporal facts with provenance beat vector-store bags for agent audit trails.
Big BrainZero to One
sakuraiben
111d ago
We cut >60% of tokens from agentic tasks by removing repeated context
Enterprise agent memory layer claiming 70% token savings over Zep and Mem0.
SlickBold Bet
longtermop
101d ago
150M Mandarin transcription model with real-time metadata detection
Dual-head Citrinet fine-tune beats running Whisper plus a separate classifier.
Niche GemBig Brain
ksingla025
101d ago
Push vs. Pull Agent Memory?
Push-based memory model challenges standard query-based agent memory patterns.
Big BrainNiche Gem
hendrixx1122
101d ago