正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

We gave Pi Code persistent memory with Mem0 Launching the Mem0 plugin for Pi Code: persistent, scoped, semantic memory across sessions and projects. It captures what matters, searches by meaning, and brings the right context back when your agent needs it. Try it out: pi install npm:@ mem0/pi-agent-plugin

mem0

20,319 subscribers

25,051 次观看 • 3 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

21 条评论

mem0 的头像

mem03 个月前

- Blog: - Mem0 Pi plugin: - Get Mem0 API key here:

Himanshu 的头像

Himanshu3 个月前

the project / session / global scope split is clean

Soumil Rathi 的头像

Soumil Rathi3 个月前

Was thinking about switching to Pi at some point; will be easier now that I have portability

Agam Pandey 的头像

Agam Pandey3 个月前

one install and it’s in the Pi terminal loop great dev-ex that i wanted actually

Kedar Vartak 的头像

Kedar Vartak3 个月前

@ShashankH_

Luis Lozano 的头像

Luis Lozano3 个月前

I haven't try mem0 prob will try but I am not sure if I like my lightweight harness starting to get bulky.

mem0 的头像

mem03 个月前

The memory layer sits outside Pi harness in Mem0, so it’s not trying to make the harness bulky or stuff everything into context. Pi only pulls memory when it’s useful, and project scope is the default so it stays tied to the repo you’re working in

Luis Lozano 的头像

Luis Lozano3 个月前

interesting will give it a try now and show the results!

mem0 的头像

mem03 个月前

feel free to reach out for any feedback/help. thanks!

Gregor 的头像

Gregor3 个月前

'captures what matters' is where it gets hard though. stale context returned confidently has burned me way more than missing context.

Ig 的头像

Ig3 个月前

memory is the missing link for useful agents. imagine combining this with @FlashPump to give tokens real utility based on long-term agent performance.

Younes Slaoui 的头像

Younes Slaoui3 个月前

/mem0-pin for migration rules is a nice touch

Komal 的头像

Komal2 个月前

Persistent, scoped memory is the missing piece for most agents today. I've been building something similar myself (vector + graph memory), so this landing natively in Pi Code is exciting. Trying it out.

MR Whale Official 🐋 的头像

MR Whale Official 🐋3 个月前

Hey! Let's collab 🚀 DM me.

Bessi 的头像

Bessi3 个月前

Usually Memory scopes are keyed on the current directory's basename, so a single project gets fragmented across git worktrees, clones, forks, and renamed directories, while unrelated directories that happen to share a basename collide into the same memory bank. The solution is to scope memory by a stable project identity instead: auto-detected from git, with an optional explicit override.

Scryrix 的头像

Scryrix3 个月前

Good wedge for agent workflows. Persistent scoped memory turns repeated setup into retrieval, which is where coding assistants start feeling durable instead of session-bound.

Jenny Wang 的头像

Jenny Wang3 个月前

Curious how you're handling project identity across git worktrees, forks, and cloned repos.

GLOBAL CRYPTO WHALE 🐳 的头像

GLOBAL CRYPTO WHALE 🐳3 个月前

LFG Follow back let’s PUMP this together

Aashi Dutt 的头像

Aashi Dutt3 个月前

Self-consolidation is underrated, and a memory that nobody cleans turns into noise 👆

Diana Crypto 的头像

Diana Crypto3 个月前

Great project. My inbox is always open.

Kevin Khachariya 的头像

Kevin Khachariya3 个月前

Oh hell yeah. I have about 15 micro pi projects now. Some of them get big enough that I will need this. Thank you.

相关视频

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇

Introducing mem0 CLI 🚀 Give your agents memory from the terminal - add, search, and retrieve memory - remember agents + developers's preference - agent-first, JSON schema-driven We built mem0 CLI to help agents remember Get started npm install -g @mem0/cli Open source 👇

Taranjeet

20,567 次观看 • 5 个月前

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

pi-web-access is an extension that provides web search (and more) for Pi coding agent. The latest update introduces a new UX pattern: you can hit `Ctrl+S` to intercept agent searches mid-flight to inspect and curate exactly what makes it into the agent conversation. pi install npm:pi-web-access

Nico Bailon

29,352 次观看 • 7 个月前

AI memory is getting f...cking illegal 10 open-source GitHub projects that stop agents from starting from zero EVERY new session 01 Mem0 ▸ → 66K+ stars 02 Hindsight ▸ → retain → recall → reflect 03 memU ▸ TURN MEMORY INTO KNOWLEDGE 04 Cognee ▸ → documents + code + conversations → knowledge graph 05 Graphiti ▸ → remembers how facts change over time 06 OpenViking ▸ MAKE THE AGENT STATEFUL 07 Letta ▸ → memory + identity across sessions 08 Letta Code ▸ REMEMBER ACROSS THE STACK 09 OpenMemory ▸ 10 Agent Memory Benchmark ▸ the loop: experience → remember → connect → retrieve → act → update 3 builds I'd actually test: coding: Hindsight → Cognee → Letta Code personal agent: Mem0 → Graphiti → Letta company brain: Cognee → Graphiti → Hindsight and this is where the sh...t gets interesting: bigger context isn't the same as memory a model can hold 1M tokens and still meet you for the first time every morning these projects change that save this before your agent forgets it ⭣

AI memory is getting f...cking illegal 10 open-source GitHub projects that stop agents from starting from zero EVERY new session 01 Mem0 ▸ → 66K+ stars 02 Hindsight ▸ → retain → recall → reflect 03 memU ▸ TURN MEMORY INTO KNOWLEDGE 04 Cognee ▸ → documents + code + conversations → knowledge graph 05 Graphiti ▸ → remembers how facts change over time 06 OpenViking ▸ MAKE THE AGENT STATEFUL 07 Letta ▸ → memory + identity across sessions 08 Letta Code ▸ REMEMBER ACROSS THE STACK 09 OpenMemory ▸ 10 Agent Memory Benchmark ▸ the loop: experience → remember → connect → retrieve → act → update 3 builds I'd actually test: coding: Hindsight → Cognee → Letta Code personal agent: Mem0 → Graphiti → Letta company brain: Cognee → Graphiti → Hindsight and this is where the sh...t gets interesting: bigger context isn't the same as memory a model can hold 1M tokens and still meet you for the first time every morning these projects change that save this before your agent forgets it ⭣

Lummox

322,301 次观看 • 5 天前

addicted to using boomerang mode (aka reverse D-Mail) in Pi these days. ctrl+alt+b enables it for the next prompt submitted -> after the prompt runs, it rewinds back to the same point with file changes intact + leaves a summary in the feed so the agent knows what happened. using it often can make the context window feel nearly unlimited. Powered by the native /tree functionality in pi. pi install pi-boomerang

addicted to using boomerang mode (aka reverse D-Mail) in Pi these days. ctrl+alt+b enables it for the next prompt submitted -> after the prompt runs, it rewinds back to the same point with file changes intact + leaves a summary in the feed so the agent knows what happened. using it often can make the context window feel nearly unlimited. Powered by the native /tree functionality in pi. pi install pi-boomerang

Nico Bailon

38,562 次观看 • 5 个月前

Mem0 is now an official Anthropic connector. No CLI, no config file, no npx mcp-add Just search "Mem0" in Claude's Connectors directory, connect your account, and every chat on Desktop, or Cowork remembers context across weeks, not just one session. Claude Code + API devs already had this. Now everyone else does too. 🧠 Try it out: → "+" → Connectors → search "Mem0"

Mem0 is now an official Anthropic connector. No CLI, no config file, no npx mcp-add Just search "Mem0" in Claude's Connectors directory, connect your account, and every chat on Desktop, or Cowork remembers context across weeks, not just one session. Claude Code + API devs already had this. Now everyone else does too. 🧠 Try it out: → "+" → Connectors → search "Mem0"

mem0

54,470 次观看 • 2 个月前

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

Jason Zhou

66,979 次观看 • 2 个月前

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Introducing watchmen. It writes the skill files your coding agents should already have from your own sessions, shared across Claude Code, Codex, and pi, so you stop paying tokens to re-explain what your agent learned last week. Local and open-source.

Dria

44,130 次观看 • 4 个月前

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

New course: Agent Memory: Building Memory-Aware Agents, built in partnership with Oracle and taught by Richmond Alake and Nacho Martínez. Many agents work well within a single session but their memory resets once the session ends. Consider a research agent working on dozens of papers across multiple days: without memory, it has no way to store and retrieve what it learned across sessions. This short course teaches you to build a memory system that enables agents to persist memory and thereby learn across sessions. You'll design a Memory Manager that handles different memory types, implement semantic tool retrieval that scales without bloating the context, and build write-back pipelines that let your agent autonomously update and refine what it knows over time. Skills you'll gain: - Build persistent memory stores for different agent memory types - Implement a Memory Manager that orchestrates how your agent reads, writes, and retrieves memory - Treat tools as procedural memory and retrieve only relevant ones at inference time using semantic search Join and learn to build agents that remember and improve over time!

Andrew Ng

162,048 次观看 • 6 个月前

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

Xiaomi just dropped a FREE CLAUDE CODE with memory that actually persists between sessions and nobody is talking about it MiMo Code dropped 4 days ago. 8k GitHub stars. Built-in free model called MiMo Auto - you just install it and it works, zero configuration, zero API keys What's inside: > persistent memory across sessions - agent picks up exactly where it stopped > subagents that spawn automatically and run in parallel > /dream extracts knowledge from your session into project memory > /distill turns your repeated workflows into reusable skills > /goal with a judge model that decides if the work is actually done - not just if the agent thinks it is How to install: > Mac / Linux: curl -fsSL | bash > Windows npm install -g MIMO-ai/cli Then run: > mimo video of me installing and running it is attached github(.)com/XiaomiMiMo/MiMo-Code

monokern

64,582 次观看 • 3 个月前

Updated pi-web-access for Pi agent with video understanding. If you're signed into Gemini in Chrome, no API keys needed for web search or video analysis. Point it at any YouTube URL or local video file (mp4, mov, etc) and ask questions about the content. pi install npm:pi-web-access

Updated pi-web-access for Pi agent with video understanding. If you're signed into Gemini in Chrome, no API keys needed for web search or video analysis. Point it at any YouTube URL or local video file (mp4, mov, etc) and ask questions about the content. pi install npm:pi-web-access

Nico Bailon

18,367 次观看 • 8 个月前

Mario (creator of Pi) thinks this video is worth watching. He's smarter than me so he's probably right. (It's about memory in code tools, and it features a crash out at how bad Claude Code's memory is)

Mario (creator of Pi) thinks this video is worth watching. He's smarter than me so he's probably right. (It's about memory in code tools, and it features a crash out at how bad Claude Code's memory is)

Theo - t3.gg

217,216 次观看 • 1 个月前

CNVS went viral for the wrong reason... the Ui is beautiful, but the CNVS cross agent memory system is world class. ultra simple & based on actual research. talking between multiple agents, codex, cursor, claude, starts to feel like one brain that actually understands your project. CNVS memory is just files agents read on demand and on Mem0's own benchmark, that approach beats Mem0 (74% vs 68.5%). Append-only JSONL every agent reads & writes directly. No DB. No embeddings. No service to be down. memory is scoped per canvas (project) increasing the specificity of the context. NO BLOAT, just clean and on demand. the least complex solution always works best.

CNVS went viral for the wrong reason... the Ui is beautiful, but the CNVS cross agent memory system is world class. ultra simple & based on actual research. talking between multiple agents, codex, cursor, claude, starts to feel like one brain that actually understands your project. CNVS memory is just files agents read on demand and on Mem0's own benchmark, that approach beats Mem0 (74% vs 68.5%). Append-only JSONL every agent reads & writes directly. No DB. No embeddings. No service to be down. memory is scoped per canvas (project) increasing the specificity of the context. NO BLOAT, just clean and on demand. the least complex solution always works best.

Max Blade

21,643 次观看 • 3 个月前

Pi-GUI now has computer use and a build in integrated terminal! v0.1.0-beta.26 To showcase the power of Mario Zechner 's Pi and OSS, I saw a pi computer-use extension on X, asked my agent to audit the extension for security, then asked it to patch pi-gui to make it compatible. Crazy how easy it was to find an oss extension for a feature I wanted, then make pi-gui work with the feature I want. Links below

Pi-GUI now has computer use and a build in integrated terminal! v0.1.0-beta.26 To showcase the power of Mario Zechner 's Pi and OSS, I saw a pi computer-use extension on X, asked my agent to audit the extension for security, then asked it to patch pi-gui to make it compatible. Crazy how easy it was to find an oss extension for a feature I wanted, then make pi-gui work with the feature I want. Links below

Matthew Lam

65,535 次观看 • 5 个月前

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Today we're shipping Oasis Desktop, a Mac app that lets you share local coding agents with your teammates. Oasis Desktop can spin up and share Claude Code, Codex, Pi, OpenCode, Kilo Code, Hermes Agent, and Devin CLI sessions as long as they're installed. Start a session with your team. Bring in Claude Code and say, “What is wrong with auth. The tests have been failing since Tuesday. Help us figure it out.” The agent reads the files and runs the test suite directly on your laptop. When it asks, “Why did we replace the session middleware last week?” your teammate can answer in the exact same session. Completely free - try it out today:

Oasis

215,176 次观看 • 1 个月前

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

I have built a Windows x64 sampling profiler for native code+C# to be used by coding agents. Why? Because it is irresponsible to let computers write code but give them no tools to evaluate the performance of their code. Stop guessing, start measuring. -> How does it work? Just point your agent to the profiler and let them measure and optimize. Or record a trace yourself and let the agent interpret the results for you. Works with Claude Code, Codex, pi, etc. The profiler also has a couple of neat features by itself like giving you estimates for how much time your code is spending on memory stalls and annotating disassembly with inlining information. Take a look and try it for free!

Sebastian Schöner

13,130 次观看 • 5 个月前

Meet Hermes Agent, the open source agent that grows with you. Hermes Agent remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access.

Meet Hermes Agent, the open source agent that grows with you. Hermes Agent remembers what it learns and gets more capable over time, with a multi-level memory system and persistent dedicated machine access.

Nous Research

3,939,468 次观看 • 7 个月前

Here’s an unedited 10-minute demo of pi-0.5 straight out of the box. We gave it just one instruction, “clean the table by putting items into the basket”, and let it run. It worked! No fine-tuning required: it handled multiple tabletop scenes robustly, with smoother and faster motions than pi-0. Full evaluations of pi0.5 and comparisons with pi-0 are on the way, stay tuned! Video credit: Kaitian Chao

Here’s an unedited 10-minute demo of pi-0.5 straight out of the box. We gave it just one instruction, “clean the table by putting items into the basket”, and let it run. It worked! No fine-tuning required: it handled multiple tabletop scenes robustly, with smoother and faster motions than pi-0. Full evaluations of pi0.5 and comparisons with pi-0 are on the way, stay tuned! Video credit: Kaitian Chao

Junyao Shi

88,054 次观看 • 1 年前

I switched my Hermes agent to 100% free local models with Magnitude It’s running Qwen 3.6 35B-A3B at ~60 tok/s on my DGX Spark. It’s free, private, and always on running background tasks Hermes set Magnitude up itself. With the CLI it: - Profiled my hardware and found the best models for it - Walked me through the options and let me decide - Switched itself over From there, models load just in time as the agent works and unload when idle Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline Copy this prompt and send it to your agent: “Set up local models for me with the Magnitude CLI. Install it with `npm i -g @magnitudedev/cli` (or my package manager), then run `magnitude docs onboarding` and follow the instructions” GitHub:

I switched my Hermes agent to 100% free local models with Magnitude It’s running Qwen 3.6 35B-A3B at ~60 tok/s on my DGX Spark. It’s free, private, and always on running background tasks Hermes set Magnitude up itself. With the CLI it: - Profiled my hardware and found the best models for it - Walked me through the options and let me decide - Switched itself over From there, models load just in time as the agent works and unload when idle Works with Pi, OpenCode, Hermes, OpenClaw, Codex, Claude Code, Oh My Pi, and Cline Copy this prompt and send it to your agent: “Set up local models for me with the Magnitude CLI. Install it with `npm i -g @magnitudedev/cli` (or my package manager), then run `magnitude docs onboarding` and follow the instructions” GitHub:

Tom Greenwald

22,752 次观看 • 1 个月前

Introducing OpenAI Dots x Heybrain. Your always-on agents now have persistent, governed memory across sessions, tools, and agents. One agent can pick up where another left off, with the right company context and permissions already in place. Powered by Brain & GPT-6.1 Sol.

Introducing OpenAI Dots x Heybrain. Your always-on agents now have persistent, governed memory across sessions, tools, and agents. One agent can pick up where another left off, with the right company context and permissions already in place. Powered by Brain & GPT-6.1 Sol.

HeyBrain

34,009 次观看 • 2 天前

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

We just launched Twin 2 500,000+ tasks automated in our first month. Now: multi-agent automation. → Master agent that orchestrates all your agents → Workspaces where agents share context and collaborate → Persistent databases for long-term memory → See and edit your agent brain for maximum control → Runner mode: scale at 1/10th the cost → Auto-generated web apps to share your agents Try it out now!

Hugo Mercier

11,226 次观看 • 7 个月前