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.

10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens 1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. 2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up... to 90% less bash noise. 3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. 4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. 5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. 6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. 7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. 8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. 9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. 10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. Save this before your next agent session burns through your subscription 👇show more

unicode

4,328 subscribers

68,057 views • 1 month ago •via X (Twitter)

Science & Technology Education Gaming

Anya Rossi• Live Now

Private livecam show

38 Comments

broke boy1 month ago

now my agent almost for free thank you

unicode1 month ago

that might be a bit of an exaggeration, but you'll definitely save money

ieatded1 month ago

Nice top 10 Saved it as always

Alex Boudot1 month ago

98k stars to make AI talk like a caveman is the clearest possible verdict on token pricing.

Hussain Hashim | Building SundayBack1 month ago

@unicodef1wn haha caveman mode is genius. reminds me of the early days when we were just making things work with whatever we had. gonna check it out!

shiqway921 month ago

+book this for the next claude code session

Lyrics1 month ago

ty for insanely gud repos

Jurly1 month ago

token savings are useful, but bad retrieval can quietly trade fewer tokens for worse answers.

Blum1 month ago

great list, found a couple of useful repos to check out

unicode1 month ago

glad you liked it, Blum

Vũ Trụ Số1 month ago

Where is gortex ?

Yumzlef1 month ago

this post made me question three assumptions i had about what this category of tool is useful for. all three assumptions turned out to be wrong

Gipp 🦅1 month ago

rtk with serena feels like the best pairing: less noise, sharper code access

Logics1 month ago

tysm 4 insanely gud repossss

RaoulDuke1 month ago

didnt know mem0 dropped a new release just three days ago with better scores

Jordan Lee1 month ago

Token efficiency is becoming an actual part of agent engineering.

Quaramly1 month ago

and which repo is best?

unicode1 month ago

code-review-graph is underrated. i use it in every one of my projects

0xbobaa1 month ago

How many more repositories are hidden from us?

unicode1 month ago

a lot. that's one of the reasons to follow me lmao

Pedro1 month ago

solid combo of repos

Eduard Lugovtsov1 month ago

This is also gigachad repo

Sebastian Buzdugan1 month ago

what failure context does rtk drop, since hidden flaky test output costs more than tokens

aibuilderhq1 month ago

token saving via caveman speak is missing the point. optimize the prompt design.

The Black Box1 month ago

who cares about token savings when the models keep getting worse? another listicle pretending tools fix broken ai

Mekasto Engineering Solutions1 month ago

Everytime I run out of token and currently working on project in which I have to stump deespseek_v4_pro What can help me in this

Camaleón Raro1 month ago

filtering repetitive CLI diagnostic outputs through a local proxy daemon dropped our background loop token consumption by ~55%. routing raw git diffs and test logs to a 32B model before context injection keeps agent response latency under 300ms. are you enforcing token budgets at the daemon level or in agent runtimes?

Suchintan Singh1 month ago

also @skyvernai if you want to cut your browser token usage down

CoderLuii1 month ago

the tokens are only half the bill. everything the agent reads gets written to disk and kept. tear apart a large claude session and roughly two thirds of it is tool results being fed back to itself, not anything the user typed. you pay to generate it, then you pay to store it.

AI Mastery Guide1 month ago

Caveman one made me laugh 😂

Clanker Tees1 month ago

The cheapest token is the log line that never enters context. I want every tool to return a receipt first: exit code, files changed, three-line summary, and a pointer to the full mess only if the agent asks.

Mr.Keyoor1 month ago

Try this

ShadowAguy1 month ago

65% fewer tokens but i still have to read it in caveman speak

Ross · 402Signal1 month ago

Context management as infrastructure instead of prompt coping is the actual unlock. Token waste is still the silent tax on most agent loops.

Yash1 month ago

Checkout this one too. Get all public apis at one place.

beamnxw ./1 month ago

gme repos

Carmelo schepis1 month ago

useful angle on token savings but double check those star counts

whemo1 month ago

even vegans will eat this meat

Related Videos

10 GitHub repos with ⭐ 1.2M+ combined stars that help you build your AI agent from scratch 1. n8n 201k⭐ - visual agent builder with 400+ integrations. Wire up multi-step AI workflows without writing a backend. 2. Hermes Agent 231k⭐ - the fastest-growing open-source agent framework of 2026. Self-improving skill loop, persistent memory across sessions. 3. Dify 152k⭐ - visual builder for agentic workflows and RAG pipelines, production-ready out of the box. 4. LangChain 144k⭐ - the standard framework for LLM apps. Chains, agents, retrieval, all in one place. 5. MetaGPT 70k⭐ - simulates an entire software company. PM, architect, engineer agents that build your app together. 6. AutoGen 60k⭐ - Microsoft's framework for multi-agent conversations and coordination. 7. OpenCode 198k⭐ - terminal coding agent, provider-agnostic across 75+ models. The go-to harness for agentic coding in 2026. 8. LlamaIndex 52k⭐ - connects your agents to your actual data. Indexing and retrieval done right. 9. CrewAI 57k⭐ - role-based crews of agents. Reads almost like plain English, no graph to learn. 10. LangGraph 40k⭐ - graph-based orchestration when you need precise control over agent state in production. Save this before you pay for another agent-building course 👇

10 GitHub repos with ⭐ 1.2M+ combined stars that help you build your AI agent from scratch 1. n8n 201k⭐ - visual agent builder with 400+ integrations. Wire up multi-step AI workflows without writing a backend. 2. Hermes Agent 231k⭐ - the fastest-growing open-source agent framework of 2026. Self-improving skill loop, persistent memory across sessions. 3. Dify 152k⭐ - visual builder for agentic workflows and RAG pipelines, production-ready out of the box. 4. LangChain 144k⭐ - the standard framework for LLM apps. Chains, agents, retrieval, all in one place. 5. MetaGPT 70k⭐ - simulates an entire software company. PM, architect, engineer agents that build your app together. 6. AutoGen 60k⭐ - Microsoft's framework for multi-agent conversations and coordination. 7. OpenCode 198k⭐ - terminal coding agent, provider-agnostic across 75+ models. The go-to harness for agentic coding in 2026. 8. LlamaIndex 52k⭐ - connects your agents to your actual data. Indexing and retrieval done right. 9. CrewAI 57k⭐ - role-based crews of agents. Reads almost like plain English, no graph to learn. 10. LangGraph 40k⭐ - graph-based orchestration when you need precise control over agent state in production. Save this before you pay for another agent-building course 👇

unicode

30,511 views • 1 month ago

I vibecoded an app in 2 days. Adding one new feature now takes me a week and a pile of tokens. Fix login, streaks break. Fix streaks, login breaks. The AI just goes in circles. Has this happened to you? It's not you. Every new chat starts with zero memory of your app. So the agent re-reads 40 files, rebuilds helpers that already exist, and misses what your change touches. Repowise indexes your codebase and keeps it updated on every commit. Even a brand new chat window knows: > what's already built > what's connected to what > what breaks if you change it Your agent reads the map instead of guessing. 27x fewer tokens to load context. 89% fewer file reads. Save the hours, the tokens, and your sanity. Connect your repo:

NAYAK

46,332 views • 5 days ago

$THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this$

THIS MIGHT BE THE #1 OPEN-SOURCE REPO FOR CLAUDE CODE RIGHT NOW. IT GIVES CLAUDE A MEMORY AND SLASHES YOUR TOKEN COST ON EVERY QUESTION The repo is safishamsi/graphify, a free open-source skill that turns any codebase into a knowledge graph Claude Code can read instantly. Instead of grepping through your files every session, Claude gets a map of how everything connects The problem it fixes: Every time you ask Claude Code about a big repo, it does the same thing, greps through dozens of files like a brute-force Ctrl+F, blows through your context window, and sometimes still misses the answer hiding in a file nobody searched. Claude Code has no memory of how your project is structured. Every session starts from zero What it does: It maps your entire codebase into a knowledge graph, capturing not just which files exist, but which functions depend on which, which modules are central, and which files cluster around the same concern. Claude queries the map instead of scanning files How it works, three passes: 1. Code structure, free and local. Tree-sitter parses your files and pulls out classes, functions, imports and call graphs. No LLM, no tokens, just your actual code mapped deterministically 2. Audio and video, if you have them. Transcribed locally and folded into the graph 3. Docs, papers, images. Here an LLM does semantic analysis, figuring out what each document means and where it fits. Only the meaning gets sent up, never your raw source It saves you money: Normally a question about a big repo makes Claude spawn explore agents that scan file after file, eating your context window and your token budget before you get an answer. With the graph already built, Claude queries the map instead of re-reading the codebase every time. Same answer, a fraction of the tokens. The graph only gets built once, then a hook rebuilds it after each commit for free, so you never pay that scanning cost again. The bigger the repo, the bigger the gap The best parts: it's a skill, so once installed Claude knows when to use it without you memorizing commands. It works on non-code folders too, point it at docs or notes and it can spin up an Obsidian vault How to add it to your Claude: 1. Install Claude Code if you haven't: npm install -g Paul Jankura-ai/claude-code 2. Add the skill: claude skill add safishamsi/graphify 3. Open your project folder and run /graphify . to build the graph 4. Optional, make it automatic: graphify hook install so the graph rebuilds after every commit That's it. Ask Claude about your repo and it reads the map instead of burning tokens on a file hunt Bookmark this

Yarchi

56,502 views • 3 months ago

5 GitHub repos with ⭐50K+ combined stars that show how far people are pushing Claude Code beyond a single coding agent 1) instructkr/claude-code 2.3K⭐ -> a research snapshot of Claude Code’s source with the internals exposed for inspection. [ ] 2) codeaashu/claude-code 3.2K⭐ -> another reconstructed Claude Code codebase built for studying how the agent works under the hood, including tools, prompts, MCP. [ ] 3) Donchitos/Claude-Code-Game-Studios 20K+⭐ -> turns one Claude Code session into a game development studio with 49 specialized agents, 73 skills, 12 hooks, 11 rules and 41 templates. [ ] 4) VoltAgent/awesome-claude-code-subagents 24K+⭐ -> 154 specialized Claude Code subagents split across 10 categories. [ ] 5) tanbiralam/claude-code 2.2K⭐ -> a research-oriented Claude Code source reconstruction for inspecting the terminal agent architecture, plugins, tools and internal implementation. [ ] Save these if you want to understand what people are actually building around Claude Code instead of just using the default CLI.

5 GitHub repos with ⭐50K+ combined stars that show how far people are pushing Claude Code beyond a single coding agent 1) instructkr/claude-code 2.3K⭐ -> a research snapshot of Claude Code’s source with the internals exposed for inspection. [ ] 2) codeaashu/claude-code 3.2K⭐ -> another reconstructed Claude Code codebase built for studying how the agent works under the hood, including tools, prompts, MCP. [ ] 3) Donchitos/Claude-Code-Game-Studios 20K+⭐ -> turns one Claude Code session into a game development studio with 49 specialized agents, 73 skills, 12 hooks, 11 rules and 41 templates. [ ] 4) VoltAgent/awesome-claude-code-subagents 24K+⭐ -> 154 specialized Claude Code subagents split across 10 categories. [ ] 5) tanbiralam/claude-code 2.2K⭐ -> a research-oriented Claude Code source reconstruction for inspecting the terminal agent architecture, plugins, tools and internal implementation. [ ] Save these if you want to understand what people are actually building around Claude Code instead of just using the default CLI.

Lummox

12,775 views • 1 month ago

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

If you're hitting Claude Code's context limit, check your terminal output before blaming your project size. Every command Claude runs dumps raw output into your context window. git status : 76% of it is noise. A failed cargo test : 155 lines becomes 3. A grep across your codebase : same story You're not running out of context because your code is too big. You're running out because the commands are bleeding you dry before you get anywhere. RTK intercepts that output, compresses it, and hands Claude a clean version instead. 60–90% fewer tokens. Same information. Runs in the background after a one-command setup. Real numbers from 2,900+ commands: average 89% compression across the board. MIT license. Free. 39k GitHub stars. rtk init -g That's it. Restart Claude Code and every command is compressed automatically.

Charlie Hills

16,692 views • 5 months ago

10 repos that cut your ai agent token bill by up to 80% 1. microsoft/LLMLingua → cuts prompt size by up to 95% compresses prompts before the api call. 20x compression. published at EMNLP + ACL. near-zero quality loss. 6,100 stars 2. mem0ai/mem0 → replaces full conversation history in context stores what matters. retrieves only what's needed. 10,000 token history → 200 token memory. per agent. 54,800 stars 3. BerriAI/litellm → routes each call to the cheapest model simple task → haiku. complex task → sonnet. tracks cost per agent, per call, per day. 45,700 stars 4. run-llama/llama_index → replaces sending full documents rag: 100-page doc → 3 relevant chunks → same answer. 98% fewer tokens per query. 49,100 stars 5. chroma-core/chroma → replaces keyword search in full context vector store. finds the closest match. feeds only that. 50-200 tokens per query instead of thousands. 27,800 stars 6. letta-ai/letta → replaces infinite context window crashes paged memory for agents. loads only relevant memory. stops your agent from hitting limits and retrying. 22,400 stars 7. guidance-ai/guidance → cuts output token bloat by 30-50% structured generation. constrains model output natively. no more 100-token prompts to get json back. 21,400 stars 8. Aider-AI/aider → replaces pasting entire codebases builds a repo map. sends only files relevant to the task. not your whole project. just what the agent needs. 44,300 stars 9. openai/tiktoken → count tokens before you send know the exact cost before the api call happens. not after the bill arrives. 18,100 stars 10. simonw/ttok → hard cap on what gets sent cli tool: count tokens, truncate to budget limit. pipe any text in. get truncated output back. 389 stars most agents are expensive not because the model is expensive. because nobody checked what was being sent to it.

10 repos that cut your ai agent token bill by up to 80% 1. microsoft/LLMLingua → cuts prompt size by up to 95% compresses prompts before the api call. 20x compression. published at EMNLP + ACL. near-zero quality loss. 6,100 stars 2. mem0ai/mem0 → replaces full conversation history in context stores what matters. retrieves only what's needed. 10,000 token history → 200 token memory. per agent. 54,800 stars 3. BerriAI/litellm → routes each call to the cheapest model simple task → haiku. complex task → sonnet. tracks cost per agent, per call, per day. 45,700 stars 4. run-llama/llama_index → replaces sending full documents rag: 100-page doc → 3 relevant chunks → same answer. 98% fewer tokens per query. 49,100 stars 5. chroma-core/chroma → replaces keyword search in full context vector store. finds the closest match. feeds only that. 50-200 tokens per query instead of thousands. 27,800 stars 6. letta-ai/letta → replaces infinite context window crashes paged memory for agents. loads only relevant memory. stops your agent from hitting limits and retrying. 22,400 stars 7. guidance-ai/guidance → cuts output token bloat by 30-50% structured generation. constrains model output natively. no more 100-token prompts to get json back. 21,400 stars 8. Aider-AI/aider → replaces pasting entire codebases builds a repo map. sends only files relevant to the task. not your whole project. just what the agent needs. 44,300 stars 9. openai/tiktoken → count tokens before you send know the exact cost before the api call happens. not after the bill arrives. 18,100 stars 10. simonw/ttok → hard cap on what gets sent cli tool: count tokens, truncate to budget limit. pipe any text in. get truncated output back. 389 stars most agents are expensive not because the model is expensive. because nobody checked what was being sent to it.

self.dll

39,554 views • 5 months ago

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 views • 10 days ago

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The reason your AI gives generic answers isn't the model. It's that your company's knowledge lives in 12 different tools and your agent can't see any of it. So here's how to build a context database your agents can actually use: 1) Pull it in: - Slack, email, meetings, docs, tickets - Auto-collected on a schedule into one place. 2) Clean it up. - An agent files what matters and drops the noise, so your brain doesn't bloat. 3) Store it as memory. - Folders of files your agents read from and write back to as they learn. 4) Point your agents at it. - Now they draft, build, and ship with full context instead of guessing. Same model. Same agent. The difference is whether it can understand your company or not. Build the database once. Everything downstream gets smarter.

The Startup Ideas Podcast (SIP) 🧃

13,666 views • 3 months ago

10 GitHub repos with 1,8M+ combined stars ⭐ that replace tools costing $30,000+/year 1. awesome ⭐495k - the list of every other list. Whatever you're looking for, it's here. 2. public-apis ⭐456k - 1,400+ free APIs across 50 categories. Weather, finance, images, games, all documented. 3. scrapling ⭐73.6k - undetectable web scraping with built-in Cloudflare bypass. Skip the $300/mo scraping API. 4. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. langflow ⭐153k - visual builder for AI agents and RAG pipelines. Drag, drop, deploy as API or MCP server. 7. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 8. open-design ⭐85k - open-source Claude Design alternative. Your coding agent becomes the design engine. 9. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 10. openhands ⭐84k - autonomous coding agent that writes, tests, and ships code. Devin costs $500/mo. This is free. Save this before you pay for another tool this list already replaces for free 👇

10 GitHub repos with 1,8M+ combined stars ⭐ that replace tools costing $30,000+/year 1. awesome ⭐495k - the list of every other list. Whatever you're looking for, it's here. 2. public-apis ⭐456k - 1,400+ free APIs across 50 categories. Weather, finance, images, games, all documented. 3. scrapling ⭐73.6k - undetectable web scraping with built-in Cloudflare bypass. Skip the $300/mo scraping API. 4. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. langflow ⭐153k - visual builder for AI agents and RAG pipelines. Drag, drop, deploy as API or MCP server. 7. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 8. open-design ⭐85k - open-source Claude Design alternative. Your coding agent becomes the design engine. 9. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 10. openhands ⭐84k - autonomous coding agent that writes, tests, and ships code. Devin costs $500/mo. This is free. Save this before you pay for another tool this list already replaces for free 👇

unicode

116,102 views • 1 month ago

10 GitHub repos with 1.4M+ ⭐ combined that the Grok Bot marketplace doesn't ship 1. public-apis ⭐480k - 1,500+ free APIs. Your bot clicks through a website for data that has an open endpoint. 2. n8n ⭐204k - 400+ integrations behind one webhook. One call instead of driving six UIs. 3. markitdown ⭐184k - PDF, docx, xlsx, pptx into clean markdown. The bot reads the file instead of screenshotting it. 4. free-for-dev ⭐137k - hundreds of services with permanent free tiers. Half your bot's stack costs nothing. 5. supabase ⭐109k - Postgres, auth and storage. /workspace holds files, not state your bots can query. 6. awesome-mcp-servers ⭐95k - the directory. Whatever the marketplace skipped, someone shipped the server. 7. docling ⭐66k - PDFs with tables and real layout, where a plain markdown pass gives you mush. 8. mem0 ⭐65k - memory shared across bots. Native memory is per-bot, so bot #4 never learns what bot #1 found out. 9. context7 ⭐62k - live docs in context. No more confident answers about an API that changed in March. 10. langfuse ⭐35k - traces and cost per run. Right now you find out what a bot spent from the invoice. Save this. The marketplace covers the obvious ones. This is the other half 👇

10 GitHub repos with 1.4M+ ⭐ combined that the Grok Bot marketplace doesn't ship 1. public-apis ⭐480k - 1,500+ free APIs. Your bot clicks through a website for data that has an open endpoint. 2. n8n ⭐204k - 400+ integrations behind one webhook. One call instead of driving six UIs. 3. markitdown ⭐184k - PDF, docx, xlsx, pptx into clean markdown. The bot reads the file instead of screenshotting it. 4. free-for-dev ⭐137k - hundreds of services with permanent free tiers. Half your bot's stack costs nothing. 5. supabase ⭐109k - Postgres, auth and storage. /workspace holds files, not state your bots can query. 6. awesome-mcp-servers ⭐95k - the directory. Whatever the marketplace skipped, someone shipped the server. 7. docling ⭐66k - PDFs with tables and real layout, where a plain markdown pass gives you mush. 8. mem0 ⭐65k - memory shared across bots. Native memory is per-bot, so bot #4 never learns what bot #1 found out. 9. context7 ⭐62k - live docs in context. No more confident answers about an API that changed in March. 10. langfuse ⭐35k - traces and cost per run. Right now you find out what a bot spent from the invoice. Save this. The marketplace covers the obvious ones. This is the other half 👇

unicode

34,610 views • 20 days ago

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

This GitHub repo is gold for anyone running Claude Code/ Codex / Any coding agent at all. My usage limits almost last double since I started using this. An open source context layer that stops your agent from reading 40 files to answer one question. No API key, no billing, no rate limit tiers. Benchmarked against Claude Code baseline: 27x token efficiency, 36% lower cost, 89% fewer file reads, 49% fewer tool calls. Every number is reproducible, the harness is in the repo. 3.5k+ stars. 50k+ pip installs, 30+ contributors, works with Claude Code, Cursor and VS Code out of the box. pip install repowise and point it at your codebase.

Srishti

12,998 views • 2 months ago

11 GitHub repos with 1.5M+ combined stars replace tools you'd otherwise pay $50K+/year for 1. free-for-dev (131k⭐) - hundreds of services with permanent free tiers. No trials, the repo's own rule. 2. public-apis (453k⭐) - 1,500+ free APIs: weather, finance, images, games. 3. awesome-selfhosted (309k⭐)- self-hosted replacements for Notion, Google Photos, Zapier and dozens more subscriptions. 4. awesome-claude-code (51k⭐) - skills, hooks, slash commands, orchestrators for Claude Code. 5. anthropics/skills (165k⭐) - the official skills repo. Start here before third-party ones. 6. awesome-mcp-servers (91k⭐) - thousands of MCP servers connecting your agent to browsers, databases, anything. 7. awesome-llm-apps (116k⭐) - 100+ ready AI agents and RAG apps with full code. 8. system-prompts-and-models-of-ai-tools (142k⭐) - leaked system prompts of Cursor, Devin, v0, Claude Code. 9. awesome-codex-skills (15k⭐) - curated Codex skills sorted by category: data & analytics, writing, productivity, development. 10. awesome (490k⭐) - the list of every other list. Whatever's missing above, it's here. Bookmark this before you pay for something that's already free 👇

11 GitHub repos with 1.5M+ combined stars replace tools you'd otherwise pay $50K+/year for 1. free-for-dev (131k⭐) - hundreds of services with permanent free tiers. No trials, the repo's own rule. 2. public-apis (453k⭐) - 1,500+ free APIs: weather, finance, images, games. 3. awesome-selfhosted (309k⭐)- self-hosted replacements for Notion, Google Photos, Zapier and dozens more subscriptions. 4. awesome-claude-code (51k⭐) - skills, hooks, slash commands, orchestrators for Claude Code. 5. anthropics/skills (165k⭐) - the official skills repo. Start here before third-party ones. 6. awesome-mcp-servers (91k⭐) - thousands of MCP servers connecting your agent to browsers, databases, anything. 7. awesome-llm-apps (116k⭐) - 100+ ready AI agents and RAG apps with full code. 8. system-prompts-and-models-of-ai-tools (142k⭐) - leaked system prompts of Cursor, Devin, v0, Claude Code. 9. awesome-codex-skills (15k⭐) - curated Codex skills sorted by category: data & analytics, writing, productivity, development. 10. awesome (490k⭐) - the list of every other list. Whatever's missing above, it's here. Bookmark this before you pay for something that's already free 👇

unicode

121,378 views • 2 months ago

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

Opus 5.5 makes this AI stack look f…cking illegal 10 GitHub repos for building everything around the model 01 zen-mcp-server ▸ → your agent debates Gemini, GPT and local models mid-task 02 claude-context ▸ → semantic code search so the agent stops grepping blind 03 wshobson/agents ▸ → a roster of subagents, each with one narrow job 04 mcp-agent ▸ → workflow patterns built around MCP tools, not around chat 05 Backlog.md ▸ → tasks live in git, so the agent and you read the same board 06 Claude Code Development Kit ▸ → hooks, subagents and MCP wired for context at scale 07 agent-rules ▸ → shared guardrails the agent inherits in every repo 08 Agent Skills ▸ → one file that teaches the agent a job, portable across tools 09 agent-scan ▸ → scans your agents, MCP servers and skills for what leaks 10 awesome-claude-code-toolkit ▸ → the map: agents, skills, commands, hooks, MCP configs the architecture: rules → context → subagents → tools → state → review → scan I'd split the stack like this: context: claude-context → Development Kit work: wshobson/agents → mcp-agent → zen-mcp-server state: Backlog.md safety: agent-rules → Agent Skills → agent-scan everyone posts the SDK and the CLI the layer that decides whether your agent survives a week is this one the model is one folder in the stack ⭣

rody

18,089 views • 3 days ago

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

i merged all my AI agents into one brain Claude Code, Codex, Gemini: one team, one memory, zero re-briefing result: 8+ hours a week back, and every agent already knows my projects, my clients and how i think here's the setup with Jarvix: 1. dump your context once: projects, clients, writing style, how you make decisions.. it builds your personal model from your actual AI interactions 2. switch agents mid-task with zero re-briefing: Claude Code builds, Codex reviews, Gemini researches, all reading the same context 3. it carries what YOU choose across sessions.. never start a chat from zero again 4. when it's time to act, it pulls the right agents together as one team instead of five separate assistants the unlock isn't another agent. it's that your context finally travels agents without shared memory are five interns on their first day, forever. agents with it are a team that's worked with you for years not more agents. one shared context that's the right bet P.S. thanks to the Jarvix team for the early access

Ronin

15,071 views • 1 month ago

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Glen is building the organizational learning and context layer for agents. Every agent session your team runs produces reasoning worth keeping, and nearly all of it is discarded the moment the window closes. Glen is the layer that unifies every agent and model your company run. Glen pulls in agent sessions from Claude Code, Codex and Cursor, plus Slack messages, GitHub prs, tickets, docs and calls. When a new agent picks up a task, Glen finds relevant prior context and injects it in the agents context window to steer it, producing knowledge work that is significantly higher quality, faster and cheaper than ever before. 29% less context and 21% faster to be exact. And Glen does more... > query the original agent behind any line of code > search every session your org has ever run > dynamic skill distillation > multiplayer agents > unified transcripts you can hand between Claude Code, Codex, and Cursor mid-task, > a company brain in Slack. Glen is in early access, sign up for the waitlist below.

Nikos

19,883 views • 1 month ago

20 GitHub repos with 2.4M+ combined stars that replace tools costing $60,000+/year 1. public-apis ⭐456k - 1,500+ free APIs across every category, weather to finance to games, all documented. 2. awesome-selfhosted ⭐312k - self-hosted replacements for Notion, Google Photos, Zapier, and dozens more paid subscriptions. 3. hermes-agent ⭐230k - self-improving personal agent with persistent memory, cron scheduling, MCP built in. Free alternative to paid always-on agent platforms. 4. n8n ⭐200k - visual automation with native AI agents. Replaces Zapier/Make entirely, self-hosted. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. dify ⭐152k - visual builder for AI agents and RAG pipelines. Skip the $500/mo no-code AI builder subscription. 7. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 8. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 9. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 10. supabase ⭐108k - Firebase alternative that's actually free to start. Auth, DB, storage in one Claude Code prompt. 11. strapi ⭐73k - open-source headless CMS, generates a full API from your content model in minutes. No Contentful bill. 12. immich ⭐110k - self-hosted photo and video backup with face recognition. Cancel the Google Photos storage plan. 13. appwrite ⭐57k - complete backend-as-a-service, self-hosted. Auth, DB, functions, storage, one prompt away from Firebase money. 14. medusa ⭐36k - full ecommerce backend, open source. Skip Shopify Plus fees entirely on your next vibe-coded store. 15. novu ⭐39k - notification infrastructure for email, SMS, push, in-app, all in one API. Replaces OneSignal's paid tiers. 16. tooljet ⭐38k - drag-and-drop internal tool builder connected to any database or API. Retool's seat pricing gone. 17. mattermost ⭐38k - self-hosted team chat built for engineering orgs. Slack without the per-seat bill. 18. outline ⭐40k - fast, clean team wiki and docs. Replaces Confluence and Notion's team plan. 19. plausible ⭐28.5k - privacy-friendly analytics, lightweight script, real dashboards. No GA360 contract needed. 20. openwork ⭐22k - open-source Claude Cowork alternative. Share skills and MCPs across Claude Code, Cursor, Codex, one setup for every agent. Save this before you pay for another tool this list already replaces for free 👇

20 GitHub repos with 2.4M+ combined stars that replace tools costing $60,000+/year 1. public-apis ⭐456k - 1,500+ free APIs across every category, weather to finance to games, all documented. 2. awesome-selfhosted ⭐312k - self-hosted replacements for Notion, Google Photos, Zapier, and dozens more paid subscriptions. 3. hermes-agent ⭐230k - self-improving personal agent with persistent memory, cron scheduling, MCP built in. Free alternative to paid always-on agent platforms. 4. n8n ⭐200k - visual automation with native AI agents. Replaces Zapier/Make entirely, self-hosted. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. dify ⭐152k - visual builder for AI agents and RAG pipelines. Skip the $500/mo no-code AI builder subscription. 7. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 8. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 9. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 10. supabase ⭐108k - Firebase alternative that's actually free to start. Auth, DB, storage in one Claude Code prompt. 11. strapi ⭐73k - open-source headless CMS, generates a full API from your content model in minutes. No Contentful bill. 12. immich ⭐110k - self-hosted photo and video backup with face recognition. Cancel the Google Photos storage plan. 13. appwrite ⭐57k - complete backend-as-a-service, self-hosted. Auth, DB, functions, storage, one prompt away from Firebase money. 14. medusa ⭐36k - full ecommerce backend, open source. Skip Shopify Plus fees entirely on your next vibe-coded store. 15. novu ⭐39k - notification infrastructure for email, SMS, push, in-app, all in one API. Replaces OneSignal's paid tiers. 16. tooljet ⭐38k - drag-and-drop internal tool builder connected to any database or API. Retool's seat pricing gone. 17. mattermost ⭐38k - self-hosted team chat built for engineering orgs. Slack without the per-seat bill. 18. outline ⭐40k - fast, clean team wiki and docs. Replaces Confluence and Notion's team plan. 19. plausible ⭐28.5k - privacy-friendly analytics, lightweight script, real dashboards. No GA360 contract needed. 20. openwork ⭐22k - open-source Claude Cowork alternative. Share skills and MCPs across Claude Code, Cursor, Codex, one setup for every agent. Save this before you pay for another tool this list already replaces for free 👇

unicode

34,424 views • 1 month ago

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 860 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 860 stars. basically nobody is looking yet bookmark this before it gone

alex

14,212 views • 1 month ago

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it 230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

alex

158,896 views • 2 months ago

someone just rebuilt claude code in pure python and made it ~230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

someone just rebuilt claude code in pure python and made it ~230x cheaper to run it's called clawcodex. a full from-scratch port of the claude code agent loop. 230k+ lines of python, MIT licensed it keeps your request prefix byte-stable, so DeepSeek's prompt cache covers your entire system + tools + history on every turn cache-hit input then bills at ~$0.0435 per 1M tokens the same 1M tokens on Claude Fable 5 runs you $10 so the longer you code, the more the cache pays off what you actually get: → 25 LLM providers (Claude, GPT, DeepSeek, GLM, local ollama) → 1M token context window → real agent loop: tools, skills, REPL, session history → one-line install, mac/linux/wsl and it's sitting at 677 stars. basically nobody is looking yet bookmark this before it gone

Argona

51,369 views • 2 months ago

this AI agentic stack is f*cking crazy 8 open-source repos that cover everything you need to run AI agents for free. not a random "top tools" dump. each one handles a different part of the job: BUILD > video-use - drop raw footage in a folder, tell Claude Code "make a launch video", get back final.mp4. it cuts filler words, adds subtitles, grades color > > Univer - a full office suite made for agents. they edit your sheets, docs and slides in a draft, you review and merge > ORCHESTRATE > Superpowers - stops your coding agent from writing code blindly. it plans first, splits work into 2–5 min tasks, tests everything > > Treg - OpenRouter, but for agent tools. one key, ~2,600 endpoints from 40+ providers: scraping, SEO, email finding > ACT > Mobile MCP - your agent controls a real iPhone or Android. taps, swipes, installs apps, records the screen > > security-audit-skill - Cloudflare's own skill that turns your coding agent into a security auditor. one agent hunts bugs, a different one double-checks every finding > REMEMBER · TEST · SHIP > Hindsight - memory that actually learns. it doesn't just recall old chats, it builds beliefs and updates them over time > > Graphify - turns your whole codebase into a map your agent can query instead of grepping files blindly. zero LLM cost to build it > the cool part isn't any single repo. it's that your agent can now: edit video -> work in Excel -> plan like a senior dev -> use 2,600 tools -> drive a phone -> audit its own code -> learn -> know your codebase you don't have to build an AI employee from scratch anymore. every part is already on GitHub. you just put it together. bookmark this before you start your next agent.

this AI agentic stack is f*cking crazy 8 open-source repos that cover everything you need to run AI agents for free. not a random "top tools" dump. each one handles a different part of the job: BUILD > video-use - drop raw footage in a folder, tell Claude Code "make a launch video", get back final.mp4. it cuts filler words, adds subtitles, grades color > > Univer - a full office suite made for agents. they edit your sheets, docs and slides in a draft, you review and merge > ORCHESTRATE > Superpowers - stops your coding agent from writing code blindly. it plans first, splits work into 2–5 min tasks, tests everything > > Treg - OpenRouter, but for agent tools. one key, ~2,600 endpoints from 40+ providers: scraping, SEO, email finding > ACT > Mobile MCP - your agent controls a real iPhone or Android. taps, swipes, installs apps, records the screen > > security-audit-skill - Cloudflare's own skill that turns your coding agent into a security auditor. one agent hunts bugs, a different one double-checks every finding > REMEMBER · TEST · SHIP > Hindsight - memory that actually learns. it doesn't just recall old chats, it builds beliefs and updates them over time > > Graphify - turns your whole codebase into a map your agent can query instead of grepping files blindly. zero LLM cost to build it > the cool part isn't any single repo. it's that your agent can now: edit video -> work in Excel -> plan like a senior dev -> use 2,600 tools -> drive a phone -> audit its own code -> learn -> know your codebase you don't have to build an AI employee from scratch anymore. every part is already on GitHub. you just put it together. bookmark this before you start your next agent.

kiosa

12,887 views • 6 days ago