Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing InsForge 2.0: The Backend for Agentic Development Our OSS backend provides databases, auth, storage, model gateway, and edge functions accessible through a context-optimized layer that agents can better understand and operate end-to-end. GitHub: Key Benchmarks (vs. Supabase MCP): - 14% higher accuracy - 1.3x faster per task -... show more

InsForge

2,959 subscribers

1,592,962 views • 7 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

50 Comments

InsForge7 months ago

Check out our repo:

InsForge7 months ago

Try now:

Hitesh Choudhary7 months ago

I recently tried v1 and I think with V2, I can push it to put pricing and launch a SAAS. Crazy good product 🤩

Imogen Ai7 months ago

Amazing share, Let's connect for collaboration

Aivetra Maxine7 months ago

Agent-native backend infrastructure is the next big layer in AI development. @insforge 2.0 looks like it's building exactly that.

InsForge7 months ago

AI mastered frontend, now we are helping it master backend

Chase Dimond | Email Marketing Nerd 📧7 months ago

This is awesome! So stoked about this!

InsForge7 months ago

Thank you! Let us know what you think :)

Shamim Hossain7 months ago

That’s impressive

InsForge7 months ago

You're impressive

Altiam Kabir7 months ago

Impressive benchmarks—14% accuracy boost and 1.3x speedup at less than half the cost is solid. Excited to test InsForge 2.0 in real projects.

Nova IA7 months ago

Very Nice ! Thanks insforge

InsForge7 months ago

🫡

Ava AI Labs7 months ago

Amazing !

InsForge7 months ago

thanks!

Yunhao Jiao7 months ago

Incredible launch! Congrats~ 🚀

Dipti Sharma7 months ago

InsForge proves great infrastructure can make complex AI systems simple to build.

InsForge7 months ago

and cheaper to build ;)

Deborah7 months ago

InsForge 2.0 looks incredible. I'm definitely checking out the repo.

Farhan Azad Shuvra7 months ago

Agent-first infrastructure is clearly the next wave. Faster tasks, fewer tokens, and lower cost — this is exactly what builders need right now. 🔥

Smiling Khan7 months ago

Setting the benchmark and expectations very high

Marry Evan7 months ago

InsForge looks like a strong platform built to simplify and accelerate agentic development.

Fermionic7 months ago

Go InsForge!🥰

InsForge7 months ago

Woohoo! 😁

- Elijah Muraoka -7 months ago

Can’t wait to try this soon for @soshiapp 😆

InsForge7 months ago

@soshiapp LFG

The AI Guru 💡7 months ago

This sounds awesome! Love seeing innovative solutions that make development smoother and more efficient. Can’t wait to check it out!

Md Riyazuddin7 months ago

Love seeing tools built specifically for agentic development.

InsForge7 months ago

AX (agent experience) is the new DX (developer experience)

Krishna Agrawal7 months ago

This is actually interesting. Letting AI handle the backend setup could save a lot of time for developers. Love that @insforge made it open-source too. ⭐

Selina7 months ago

CONGRATS!!!!

Alejandro Martinez | IA7 months ago

This is very interesting

Salma ✨7 months ago

Awesome

Kylee7 months ago

This could make agentic development much more efficient. Great work!

InsForge7 months ago

that's the goal :) thanks!

Salma ✨7 months ago

That's very impressive

Keybzs7 months ago

Great one

Emma Uses AI7 months ago

Cool !

Parul Gautam7 months ago

14% higher accuracy and 2.4x fewer tokens, InsForge 2.0 is exactly the efficient OSS backend developers have been waiting for!

Rony7 months ago

Congratulations on the launch 👏

InsForge7 months ago

woohoo! 🎉

OtakuMachine7 months ago

Nice @insforge

InsForge7 months ago

Nice 😎

VICK MELLY🇰🇪🇷🇺7 months ago

I will check this one out

InsForge7 months ago

Let us know what you think!

54NZ4 months ago

Cannot live a day without @insforge. I am hooked

InsForge4 months ago

🫶

Enzo Sanchez | IA7 months ago

Vamos @insforge !

InsForge7 months ago

vamos!

Mayank Agarwal 💡7 months ago

Agent-native infrastructure is the next layer of the AI stack. Tools that reduce tokens + latency will win.

Related Videos

Introducing InsForge Backend Branching. We made agentic coding production-safe. Your agent creates isolated backend branches when working. Every backend service, policy, and config is copied into a secure, isolated environment. Review PR-style diffs. Merge only when ready.

Introducing InsForge Backend Branching. We made agentic coding production-safe. Your agent creates isolated backend branches when working. Every backend service, policy, and config is copied into a secure, isolated environment. Review PR-style diffs. Merge only when ready.

InsForge

62,391 views • 4 months ago

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.

Introducing Diagnose and Debug. Give your agent first-party backend context: health metrics, logs, errors, database checks, and more. Your coding agent catches backend issues now, then fixes them by working with your dedicated InsForge debugging agent. Agent <> Agent.

InsForge

53,090 views • 4 months ago

Claude Code used 3x fewer tokens with one change: - Before: 10.4M tokens · 10 errors · $9.21 cost - After: 3.7M tokens · 0 errors · $2.81 cost I used InsForge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). With Supabase, tables, RLS policies, auth providers, storage buckets, and edge functions were retrieved through separate calls. Each response entered the conversation history, so later calls carried more context. But InsForge returned the backend topology in one metadata call of roughly 500 tokens. InsForge repo: (don't forget to star it 🌟) Its instructions were also split into narrow skills for CLI operations, debugging, SDK usage, and integrations. Claude loaded only the instructions needed for the task. The CLI returned structured JSON with semantic exit codes as well. This made it clear whether a failure came from the operation itself or the code being executed, avoiding several retry loops. The token savings essentially came from replacing repeated backend discovery and debugging calls with one structured view of the backend. I wrote a detailed walkthrough of both builds, including where the extra calls, tokens, and errors came from. Read it below.

Claude Code used 3x fewer tokens with one change: - Before: 10.4M tokens · 10 errors · $9.21 cost - After: 3.7M tokens · 0 errors · $2.81 cost I used InsForge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). With Supabase, tables, RLS policies, auth providers, storage buckets, and edge functions were retrieved through separate calls. Each response entered the conversation history, so later calls carried more context. But InsForge returned the backend topology in one metadata call of roughly 500 tokens. InsForge repo: (don't forget to star it 🌟) Its instructions were also split into narrow skills for CLI operations, debugging, SDK usage, and integrations. Claude loaded only the instructions needed for the task. The CLI returned structured JSON with semantic exit codes as well. This made it clear whether a failure came from the operation itself or the code being executed, avoiding several retry loops. The token savings essentially came from replacing repeated backend discovery and debugging calls with one structured view of the backend. I wrote a detailed walkthrough of both builds, including where the extra calls, tokens, and errors came from. Read it below.

Avi Chawla

65,041 views • 1 month ago

We’re building the agent-native alternative to AWS, but it's actually good. - 33,000+ projects created (10% WoW growth) - 2x weekly active projects (2000 → 4000+) - 11,000+ GitHub stars (5x in the last 3 months) - faster than React, Supabase, and Linux Introducing InsForge ↓

We’re building the agent-native alternative to AWS, but it's actually good. - 33,000+ projects created (10% WoW growth) - 2x weekly active projects (2000 → 4000+) - 11,000+ GitHub stars (5x in the last 3 months) - faster than React, Supabase, and Linux Introducing InsForge ↓

InsForge

603,836 views • 4 months ago

Claude Code used 3x fewer tokens with one change: - Before: 10.4M tokens · 10 errors · $9.21 - After: 3.7M tokens · 0 errors · $2.81 I used Insforge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). Repo:

Claude Code used 3x fewer tokens with one change: - Before: 10.4M tokens · 10 errors · $9.21 - After: 3.7M tokens · 0 errors · $2.81 I used Insforge Skills + CLI as the backend context engineering layer for Claude Code (open-source and local). Repo:

Avi Chawla

295,077 views • 6 months ago

Introducing InsForge Compute. Deploy long-running backend services as Docker containers via your coding agent. It writes the Dockerfile, builds the image, injects env vars, runs the container, and returns a live URL. All in under 60 seconds.

Introducing InsForge Compute. Deploy long-running backend services as Docker containers via your coding agent. It writes the Dockerfile, builds the image, injects env vars, runs the container, and returns a live URL. All in under 60 seconds.

InsForge

1,511,264 views • 4 months ago

Today we’re launching 4 open-source Next.js app templates: 1. Basic starter 2. Chatbot 3. CRM 4. Ecommerce We made building real full-stack apps even easier on InsForge. Try one in your next project: npx @insforge/cli create Thread below with all 4 repos ↓

Today we’re launching 4 open-source Next.js app templates: 1. Basic starter 2. Chatbot 3. CRM 4. Ecommerce We made building real full-stack apps even easier on InsForge. Try one in your next project: npx @insforge/cli create Thread below with all 4 repos ↓

InsForge

671,992 views • 6 months ago

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

Avi Chawla

113,330 views • 4 months ago

ColorOS 17 vs ColorOS 16 Faster foreground, faster app navigation, and faster loading of third-party app photo albums. The backend is more stable, with a brand-new memory backend, more accurate backend retention, and better retention quality.

TECH INFO

18,284 views • 1 month ago

Introducing InsForge Payments. Your coding agent can now set up Stripe payments for your app using InsForge. Describe your pricing and watch it create products and prices in Stripe, add checkout, and set up billing portal sessions. Test first. Go live when ready.

Introducing InsForge Payments. Your coding agent can now set up Stripe payments for your app using InsForge. Describe your pricing and watch it create products and prices in Stripe, add checkout, and set up billing portal sessions. Test first. Go live when ready.

InsForge

674,924 views • 4 months ago

The Neon backend is GA. A complete set of primitives for apps and agents built around the database, with open standards, no lock-in, and branching-first by design. Starting with: Lakebase Postgres, Object Storage, Functions, Managed Better Auth, and AI Gateway. More to come.

The Neon backend is GA. A complete set of primitives for apps and agents built around the database, with open standards, no lock-in, and branching-first by design. Starting with: Lakebase Postgres, Object Storage, Functions, Managed Better Auth, and AI Gateway. More to come.

Neon

28,250 views • 1 month ago

.InsForge turns your coding agent into a principal backend engineer. Backend servers, database, LLM gateway, frontend deployment, and more. Every primitive built for how coding agents actually work, so they can run your entire infrastructure. Congrats on the launch, Hang Huang ☁️ & Tony Chang ☁️!

.InsForge turns your coding agent into a principal backend engineer. Backend servers, database, LLM gateway, frontend deployment, and more. Every primitive built for how coding agents actually work, so they can run your entire infrastructure. Congrats on the launch, Hang Huang ☁️ & Tony Chang ☁️!

Y Combinator

152,008 views • 5 months ago

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

i just built a 4-agent software team. everything runs from Telegram and gets managed on a kanban board. a project manager who plans the work, a backend developer, a frontend developer, and a tester. the PM reads a goal, breaks it into linked tasks, and assigns each to the right agent. the thing that makes them a team instead of four strangers is a shared kanban board. every task is a row that survives crashes, and when an agent finishes, it writes a summary of what it built and what the next agent needs to know. the next agent reads that summary before it starts. so the frontend developer never has to guess the API shape, and the tester knows exactly what to verify. the hardest part was not the coordination. it was building an agent that could actually act like a backend engineer. a backend engineer stands up a database, wires auth, manages storage, deploys functions, and keeps all of it consistent while the rest of the team builds on top. an agent doing this from scratch drowns. it burns its context window remembering which tables exist and which endpoint it created three steps ago, and the work degrades fast. so the backend agent needs a backend built for agents, not for humans clicking through a dashboard. that is where InsForge came in. it is an open-source, agent-native backend, and i added it to my backend developer agent as a skill. a skill is a step-by-step guide that teaches the agent how to do a specific kind of work. with InsForge installed, the agent stopped improvising infrastructure and followed a reliable path: create the project, define the database, set up auth, deploy functions. to test the whole team, i had them build a working Google Docs clone, AI features included. the backend agent spun up the full service on its own. database tables, user auth, document handling, and edge functions running real TypeScript, all in one dashboard. the frontend agent read that summary and built the UI on top of it, and the tester closed the loop. the result was a backend an agent could reason about end to end, instead of one it kept getting lost inside. if you are building an AI backend engineer, InsForge is worth a look, it's 100% open-source. InsForge GitHub: (don't forget to star 🌟) the full article on Hermes Kanban: Mission Control for your Agents is quoted below.

Akshay 🚀

123,101 views • 4 months ago

Introducing Coldtea. The ADE for shipping self-driving software. Purpose-built for the entire software lifecycle. Other IDEs optimise for one thing: Build. Run more agents in parallel, ship faster, orchestrate better. But software engineering is not just about building. Coldtea AI brings your coding agents, agentic end-to-end testing, and production monitoring agents into ONE development environment, so you can move at agent speed without breaking anything.

Introducing Coldtea. The ADE for shipping self-driving software. Purpose-built for the entire software lifecycle. Other IDEs optimise for one thing: Build. Run more agents in parallel, ship faster, orchestrate better. But software engineering is not just about building. Coldtea AI brings your coding agents, agentic end-to-end testing, and production monitoring agents into ONE development environment, so you can move at agent speed without breaking anything.

Ohans Emmanuel

441,533 views • 2 months ago

Supabase MCP server now supports creating and deploying Edge Functions! Refresh your MCP server and make sure you have the `deploy_edge_function` tool, and you are good to go! Just ask your AI tool to create an edge function or a backend, and it will create it for you!

Supabase MCP server now supports creating and deploying Edge Functions! Refresh your MCP server and make sure you have the `deploy_edge_function` tool, and you are good to go! Just ask your AI tool to create an edge function or a backend, and it will create it for you!

Tyler Shukert

29,248 views • 1 year ago

Supabase now has an official MCP Server! This means you can create, edit, and connect a Supabase project to your app from your AI IDE like Cursor or Windsurf! We will also be adding more features to the MCP server, such as Edge Functions and Storage, in the near future!

Supabase now has an official MCP Server! This means you can create, edit, and connect a Supabase project to your app from your AI IDE like Cursor or Windsurf! We will also be adding more features to the MCP server, such as Edge Functions and Storage, in the near future!

Tyler Shukert

85,127 views • 1 year ago

FlutterFlow 7.0 shipping today. 250M+ users running on apps built with FlutterFlow. version 7.0 focuses on two things every developer cares about: - build faster: MCP support, Test Pilot AI QA. - build better: Supabase Edge Functions, Test Mode upgrades, Smarter AI Agents, Project organization. now go build.

FlutterFlow 7.0 shipping today. 250M+ users running on apps built with FlutterFlow. version 7.0 focuses on two things every developer cares about: - build faster: MCP support, Test Pilot AI QA. - build better: Supabase Edge Functions, Test Mode upgrades, Smarter AI Agents, Project organization. now go build.

FlutterFlow

334,295 views • 4 months ago

Introducing 🦀 CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents 🦀 CRAB provides an end-to-end and easy-to-use framework to build multimodal agents, operate environments, and create benchmarks to evaluate them, featuring three key components: - 🔀 Cross-environment support - agents can operate tasks in 📱 Android and 💻 Ubuntu. - 🕸️ Graph evaluator - provides a fine-grain evaluation metric for agents. - 🤖 Task generation - composes subtasks to automatically generate tasks. By connecting all devices to agents, 🦀CRAB unlocks greater capabilities for human-like tasks than ever before. Use 🦀 CRAB to benchmark your multimodal agents! - 👨‍💻 Check out the repository: - 📝 Read the paper: - 🌐 Find out more via the project page: - 🐫 Join our community:

Introducing 🦀 CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents 🦀 CRAB provides an end-to-end and easy-to-use framework to build multimodal agents, operate environments, and create benchmarks to evaluate them, featuring three key components: - 🔀 Cross-environment support - agents can operate tasks in 📱 Android and 💻 Ubuntu. - 🕸️ Graph evaluator - provides a fine-grain evaluation metric for agents. - 🤖 Task generation - composes subtasks to automatically generate tasks. By connecting all devices to agents, 🦀CRAB unlocks greater capabilities for human-like tasks than ever before. Use 🦀 CRAB to benchmark your multimodal agents! - 👨‍💻 Check out the repository: - 📝 Read the paper: - 🌐 Find out more via the project page: - 🐫 Join our community:

CAMEL-AI.org

72,807 views • 2 years ago

Google Antigravity is our new agentic development platform. It helps developers build faster by collaborating with AI agents that can autonomously operate across the editor, terminal, and browser. It uses Gemini 3 Pro 🧠 to reason about problems, Gemini 2.5 Computer Use 💻 for end-to-end execution, and Nano Banana 🍌 for image generation.

Google Antigravity is our new agentic development platform. It helps developers build faster by collaborating with AI agents that can autonomously operate across the editor, terminal, and browser. It uses Gemini 3 Pro 🧠 to reason about problems, Gemini 2.5 Computer Use 💻 for end-to-end execution, and Nano Banana 🍌 for image generation.

Google DeepMind

198,575 views • 11 months ago

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

AI agents work better when they bring in context step by step. With Box Agent skills and progressive disclosure of LangChain skills, developers can quickly build AI agents that load the right skill at the right time, stay grounded in Box content, and keep access tightly scoped. Less context bloat. More control. Faster enterprise AI development.

Box

627,810 views • 6 months ago