pump.fun logomark
pump.fun logomark
Playful 3D scene of a smiling green character running with meme-inspired figures like a Shiba Inu and hippo across a sunny grassy hill

Welcome to Pump.fun!

Pump lets anyone create coins, giving everyone equal access to buy and sell from the start. Prices can move quickly, so trade carefully.

By clicking this button, you agree to the Terms and Conditions, Privacy Policy, and certify that you are over 18 years old.

pump.fun logomark
  • Home
  • Explore
  • PerpsNew
  • PacksNew
  • Leaderboard
  • Live
Discover
  • GO
  • Mayhem
  • Holder rewardsNew
  • Watchlist
  • Orders
  • $PUMP
  • Terminal
Trade faster. Pump is better on mobile.
pump.fun logomark
Signed in

Resources

  • Guides
  • PumpSwap
  • Fees
  • Revenue
  • Tech updates
  • Wallet sign-in changes

Legal

  • Privacy policy
  • Terms of service
  • Tokenized agent disclaimer
  • Livestream policy
  • DMCA policy
  • Trademark guidelines
  • Charity coins
  • Go.fun terms
Blog

© Pump.fun 2026

© Pump.fun 2026

Blog

We value your privacy

This site uses cookies to improve your browsing experience, analyze site traffic, and show personalized content.

Feed

  • z1nger
    z1nger4m

    wow @zinc is here

    Coin image for FwVsiYsWBDCs4QifGcDRGGxQ3xh6CYLnWWFLUDiupump

    Nеil

    Nеil The Lеmur

    Position

    $275.87

    Profit

    +$138.92

    744$40.6K MC
    z1nger
    z1nger3m

    I MIGHT HAVE FOUND THE NEXT PUNCH Also their Zoo asking for funds, because the costs of containing animals have rapidly increased. Neil, a lemur from the San Francisco Zoo, is starting to go viral for carrying his plushie everywhere, just like Punch! People are already memeing and loving him in the comments. He's not GIGA VIRAL yet, but the potential is definitely there. We haven't had a major runner for him yet, and the market needs an animal runner. Donategg also has the zoo's charity, making it even better!

  • mitch
    mitch1h

    potentially, a free 6x

    13.9K
  • wirelyss
    wirelyss
    16m

    Best CA I could find given the options. Huge huge trend and buying addiction on TikTok, reminds me of labubu but bigger. everyone has and buys squishies and there are styles. Rare ones, no rebound, butter, crunchy peanut, taba squish, cheese, clay, wax, hard shell, you name it Don't love the fees but at least they paid dex. Maybe itll inspire someone to do/claim cto

    Coin image for 2GDKok8kwNcfLWrtZ6AMeiecqt5WapzJhcLXaL4Qpump

    Squishy

    Squishy

    Position

    $1,775.45

    Profit

    +$1,655.92

    3,612$32.2K MC
  • AestheticGoat
    AestheticGoat
    11m

    Dogecoin creator endorsed🙌

    Coin image for FVzqGqRmr4UH1Fif6dewmwbJ1p4YUZCu8dcw4Efopump

    HOGE

    Hogecoin

    Position

    $410.00

    Profit

    −$11.43

    1,352$260K MC
    AestheticGoat
    AestheticGoat9m

    MILLIONS

  • ely
    ely
    31m

    Ok I think all the bundles out Funny meme I keep seeing it in gifs that slander my goats chairman Cupsey and Dior

    Coin image for 2kWx47CUrcXtzptFNnbSXKq3vo1ebqyLBhRytKRGpump

    WIGGLES

    Jiggly Wiggly Dog

    Position

    $4,140.58

    Profit

    +$2,914.75

    5,472$176K MC
    ely
    ely5m

    Billions will wiggle Return to memes

  • card100x
    card100x
    3m

    insider wallets from billy in this, hmmm

    Coin image for Ahc52P7m5n9tsEy2u52AUZiUCjTiZ6vMymbuDWjDHpay

    Billy

    Shibetoshi Nakamoto

    Position

    $37.77

    Profit

    +$9.38

    393$29.1K MC
  • paulo10835
    paulo108352m

    Could be very good lets see after bond it it holds then boom

    Coin image for FwVsiYsWBDCs4QifGcDRGGxQ3xh6CYLnWWFLUDiupump

    Nеil

    Nеil The Lеmur

    Position

    $1,715.12

    Profit

    +$1,366.06

    376$40.6K MC
  • Flayzzz
    Flayzzz
    57m

    What if we all keep calling the same coin?

    Coin image for 5qRxJ9W45zUrUtGGDneysiRBKZaceNriEqVUei1Rpump

    SAME

    The Same Coin

    Position

    $1,497.76

    Profit

    +$1,274.02

    2,474$40.8K MC
    Flayzzz
    Flayzzz2m

    This has PVE potential fr

  • Bondzy
    Bondzy
    1m

    found the money glitch

    Coin image for 4ymRDbgd9gGWztUVyj7Da3uAhUJ8a6YE5Tu7ncdtpump

    HESOYAM

    infinite money glitch

    Position

    $116.86

    Profit

    +$6.68

    40$3.72K MC
  • auxy
    auxy15m

    This goes way higher

    Coin image for 2GDKok8kwNcfLWrtZ6AMeiecqt5WapzJhcLXaL4Qpump

    Squishy

    Squishy

    Position

    $31.51

    Profit

    +$1.82

    661$32.2K MC
  • RippleSixLand
    RippleSixLand
    1m

    Fees to dogecoin creator. As he agreed to claim

    Coin image for Ahc52P7m5n9tsEy2u52AUZiUCjTiZ6vMymbuDWjDHpay

    Billy

    Shibetoshi Nakamoto

    Position

    $24.61

    Profit

    +$0.11

    48$29.1K MC
    RippleSixLand
    RippleSixLand27s

    This send now

  • Goodcallouts
    Goodcallouts3m

    runner.

    Coin image for FwVsiYsWBDCs4QifGcDRGGxQ3xh6CYLnWWFLUDiupump

    Nеil

    Nеil The Lеmur

    Position

    $318.10

    Profit

    +$67.97

    481$40.6K MC
    Goodcallouts
    Goodcallouts49s

    good dev also

BUAGENTSDK bu-agent-sdk

Unknown creation dateView Count 1
DevChain and launchpad: Solana
$1.62K
Holders317
$1.62K
Holders317
317 holders
Price change—
Volume—
—buys
—sells
—buy vol
—sell vol
—buyers
—sellers
Creator
7CCX…fS4B's profile picture7CCX…fS4B
Loading…
Actions
Holders
317
Price change—
Volume—
—buys
—sells
—buy vol
—sell vol
—buyers
—sellers
Creator
7CCX…fS4B's profile picture7CCX…fS4B

About bu-agent-sdk (BUAGENTSDK)

Chain
Solana
Price
$0.000001625 USD
Market cap
$1.62K
Creator
7CCX…fS4B
Contract address
DqEMsw7JBiCnLakUbNcZ563HmE4m9bdCBWqhhDnLswrm

Description

# bu-agent-sdk _An agent is just a for-loop._ ![Agent Loop](./static/agent-loop.png) The simplest possible agent framework. No abstractions. No magic. Just a for-loop of tool calls. The framework powering [BU.app](https://bu.app). ## Install ```bash uv sync ``` or ```bash uv add bu-agent-sdk ``` ## Quick Start ```python import asyncio from bu_agent_sdk import Agent, tool, TaskComplete from bu_agent_sdk.llm import ChatAnthropic @tool("Add two numbers") async def add(a: int, b: int) -> int: return a + b @tool("Signal task completion") async def done(message: str) -> str: raise TaskComplete(message) agent = Agent( llm=ChatAnthropic(model="claude-sonnet-4-20250514"), tools=[add, done], ) async def main(): result = await agent.query("What is 2 + 3?") print(result) asyncio.run(main()) ``` ## Philosophy **The Bitter Lesson:** All the value is in the RL'd model, not your 10,000 lines of abstractions. Agent frameworks fail not because models are weak, but because their action spaces are incomplete. Give the LLM as much freedom as possible, then vibe-restrict based on evals. ## Features ### Done Tool Pattern The naive "stop when no tool calls" approach fails. Agents finish prematurely. Force explicit completion: ```python @tool("Signal completion") async def done(message: str) -> str: raise TaskComplete(message) agent = Agent( llm=llm, tools=[..., done], require_done_tool=True, # Autonomous mode ) ``` ### Ephemeral Messages Large tool outputs (browser state, screenshots) blow up context. Keep only the last N: ```python @tool("Get browser state", ephemeral=3) # Keep last 3 only async def get_state() -> str: return massive_dom_and_screenshot ``` ### Simple LLM Primitives ~300 lines per provider. Same interface. Full control: ```python from bu_agent_sdk.llm import ChatAnthropic, ChatOpenAI, ChatGoogle # All implement BaseChatModel agent = Agent(llm=ChatAnthropic(model="claude-sonnet-4-20250514"), tools=tools) agent = Agent(llm=ChatOpenAI(model="gpt-4o"), tools=tools) agent = Agent(llm=ChatGoogle(model="gemini-2.0-flash"), tools=tools) ``` ### Context Compaction Auto-summarize when approaching context limits: ```python from bu_agent_sdk.agent import CompactionConfig agent = Agent( llm=llm, tools=tools, compaction=CompactionConfig(threshold_ratio=0.80), ) ``` ### Dependency Injection FastAPI-style, type-safe: ```python from typing import Annotated from bu_agent_sdk import Depends def get_db(): return Database() @tool("Query users") async def get_user(id: int, db: Annotated[Database, Depends(get_db)]) -> str: return await db.find(id) ``` ### Streaming Events ```python from bu_agent_sdk.agent import ToolCallEvent, ToolResultEvent, FinalResponseEvent async for event in agent.query_stream("do something"): match event: case ToolCallEvent(tool=name, args=args): print(f"Calling {name}") case ToolResultEvent(tool=name, result=result): print(f"{name} -> {result[:50]}") case FinalResponseEvent(content=text): print(f"Done: {text}") ``` ## Claude Code in 100 Lines A sandboxed coding assistant with dependency injection: ```python import asyncio import subprocess from dataclasses import dataclass from pathlib import Path from typing import Annotated from bu_agent_sdk import Agent from bu_agent_sdk.llm import ChatAnthropic from bu_agent_sdk.tools import Depends, tool @dataclass class SandboxContext: """All file operations restricted to root_dir.""" root_dir: Path working_dir: Path def resolve_path(self, path: str) -> Path: resolved = (self.working_dir / path).resolve() resolved.relative_to(self.root_dir) # Raises if escapes return resolved def get_sandbox() -> SandboxContext: raise RuntimeError("Override via dependency_overrides") @tool("Execute shell command") async def bash(command: str, ctx: Annotated[SandboxContext, Depends(get_sandbox)]) -> str: result = subprocess.run(command, shell=True, capture_output=True, text=True, cwd=ctx.working_dir) return result.stdout + result.stderr or "(no output)" @tool("Read file contents") async def read(path: str, ctx: Annotated[SandboxContext, Depends(get_sandbox)]) -> str: return ctx.resolve_path(path).read_text() @tool("Write file contents") async def write(path: str, content: str, ctx: Annotated[SandboxContext, Depends(get_sandbox)]) -> str: ctx.resolve_path(path).write_text(content) return f"Wrote {len(content)} bytes" @tool("Find files by glob pattern") async def glob(pattern: str, ctx: Annotated[SandboxContext, Depends(get_sandbox)]) -> str: files = [str(f.relative_to(ctx.root_dir)) for f in ctx.working_dir.glob(pattern)] return "\n".join(files) or "No matches" @tool("Signal task completion") async def done(message: str) -> str: from bu_agent_sdk.agent import TaskComplete raise TaskComplete(message) async def main(): # Create sandbox root = Path("./sandbox") root.mkdir(exist_ok=True) ctx = SandboxContext(root_dir=root.resolve(), working_dir=root.resolve()) agent = Agent( llm=ChatAnthropic(model="claude-sonnet-4-20250514"), tools=[bash, read, write, glob, done], system_prompt=f"Coding assistant. Working dir: {ctx.working_dir}", dependency_overrides={get_sandbox: lambda: ctx}, ) print("Agent ready. Ctrl+C to exit.") while True: task = input("\n> ") async for event in agent.query_stream(task): if hasattr(event, "tool"): print(f" → {event.tool}") elif hasattr(event, "content") and event.content: print(f"\n{event.content}") asyncio.run(main()) ``` See [`bu_agent_sdk/examples/claude_code.py`](./bu_agent_sdk/examples/claude_code.py) for the full version with grep, edit, and todo tools. ## Examples See [`bu_agent_sdk/examples/`](./bu_agent_sdk/examples/) for more: - `claude_code.py` - Full Claude Code clone with sandboxed filesystem - `dependency_injection.py` - FastAPI-style dependency injection ## The Bitter Truth Every abstraction is a liability. Every "helper" is a failure point. The models got good. Really good. They were RL'd on computer use, coding, browsing. They don't need your guardrails. They need: - A complete action space - A for-loop - An explicit exit - Context management **The bitter lesson: The less you build, the more it works.** ## License MIT ## Credits Built by [Browser Use](https://browser-use.com). Inspired by reverse-engineering Claude Code and Gemini CLI. Source: https://github.com/browser-use/agent-sdk

Actions
inertshark17431's profile pictureinertshark1743118.1M1.81%$291.81%$105K$4.15K
6ESX8s's profile picture6ESX8s10.6M1.06%$171.06%$4.75K$50
9d44pd's profile picture9d44pd10.5M1.05%$171.05%$6.07K$64
fitshark74349's profile picturefitshark743496.75M0.68%$110.68%$77.7K$673
74vdo8's profile picture74vdo85.11M0.51%$80.51%$13.5K$69
jdcjdcl's profile picturejdcjdcl1.33M0.13%$20.13%$10.8K$14
assignedcrab903's profile pictureassignedcrab9031.25M0.13%$20.13%$94.5K$2.7K
whitetard's profile picturewhitetard614K0.06%$1.000.06%$485K$298
GSL's profile pictureGSL247K0.02%$0.400.02%$273K$100
8f8wdi's profile picture8f8wdi225K0.02%$0.370.02%$246K$148
brrre's profile picturebrrre208K0.02%$0.340.02%$96K$20
changedtuna5407's profile picturechangedtuna5407175K0.02%$0.280.02%$1.13M$198