Meta Claw

it learns and EVOLVES. Inspired by how brains learn. Meta-learn and evolve your 🦞 from every conversation in the wild. No GPU required.

[Meta Claw @MetaClawdev]

MetaClaw is an agent that meta-learns and evolves in the wild. Just talk to your agent as you normally would MetaClaw turns every live conversation into a learning signal, enabling the agent to continuously improve through real-world deployment rather than offline training alone.

Under the hood, it places your model behind a proxy that intercepts interactions from your personal agent (OpenClaw, CoPaw, IronClaw, PicoClaw, ZeroClaw, NanoClaw, NemoClaw, or any OpenAI-compatible client), injects relevant skills at each turn, and meta-learns from accumulated experience. For Anthropic-native agents like NanoClaw, MetaClaw also exposes a /v1/messages Anthropic-compatible endpoint so the full pipeline works without any agent-side changes. Skills are summarized automatically after each session; with RL enabled, a meta-learning scheduler defers weight updates to idle windows so the agent is never interrupted during active use.

No GPU cluster required. MetaClaw works with any OpenAI-compatible LLM API out of the box, and uses a Tinker-compatible backend for cloud-based LoRA training. Tinker is the default reference path; MinT and Weaver can be enabled through separate compatibility packages when needed.

CA : 0xe9ce29bbAa23185eAAdcDF30708A62B236082E22
https://t.co/wFrjFYi2co

[Meta Claw @MetaClawdev]

https://t.co/OYn8QrDDNd

[Meta Claw @MetaClawdev]

Guess who’s back?

[Meta Claw @MetaClawdev]

The MetaClaw framework combines online reinforcement learning, skill injection, and intelligent scheduling into a unified system, providing a fundamentally new paradigm for building adaptive, autonomous AI agents that grow smarter with every interaction.

[Meta Claw @MetaClawdev]

MetaClaw is an open-source AI agent framework developed by AIMING Lab at the University of North Carolina at Chapel Hill. At its core, MetaClaw enables AI agents to achieve self-evolution and meta-learning by inserting a transparent proxy between users and large language models (LLMs). Every daily conversation becomes a learning signal, allowing agents to continuously improve during real-world deployment rather than relying solely on offline training.

[Meta Claw @MetaClawdev]

Traditional reinforcement learning approaches require massive annotated datasets and expensive GPU clusters. MetaClaw eliminates these barriers. Through its innovative architecture, agents accumulate experience from real-time user interactions, automatically extract and inject new skills, and achieve continuous capability improvement — all without pre-built datasets or dedicated GPU infrastructure.

[Meta Claw @MetaClawdev]

$META is available on @base and we’re choose @flaunchgg.

trade here : https://t.co/OYn8QrDDNd

[Meta Claw @MetaClawdev]

MetaClaw is an agent that meta-learns and evolves in the wild. Just talk to your agent as you normally would MetaClaw turns every live conversation into a learning signal, enabling the agent to continuously improve through real-world deployment rather than offline training alone.

Under the hood, it places your model behind a proxy that intercepts interactions from your personal agent (OpenClaw, CoPaw, IronClaw, PicoClaw, ZeroClaw, NanoClaw, NemoClaw, or any OpenAI-compatible client), injects relevant skills at each turn, and meta-learns from accumulated experience. For Anthropic-native agents like NanoClaw, MetaClaw also exposes a /v1/messages Anthropic-compatible endpoint so the full pipeline works without any agent-side changes. Skills are summarized automatically after each session; with RL enabled, a meta-learning scheduler defers weight updates to idle windows so the agent is never interrupted during active use.

No GPU cluster required. MetaClaw works with any OpenAI-compatible LLM API out of the box, and uses a Tinker-compatible backend for cloud-based LoRA training. Tinker is the default reference path; MinT and Weaver can be enabled through separate compatibility packages when needed.

CA : 0xe9ce29bbAa23185eAAdcDF30708A62B236082E22
https://t.co/wFrjFYi2co

[Meta Claw @MetaClawdev]

Start in minutes:
Everything you need to run MetaClaw. No PhD, no GPU cluster.

Train from real usage
Learns directly from live conversations. No static datasets, no offline retraining.

Skill injection:
Relevant skills injected into every turn. Instant behavior improvement without retraining.

Skill evolution:
Auto-generates new skills from failures using an LLM. Gets smarter over time.

No GPU cluster:
Training offloaded to Tinker cloud. Any machine with internet access can run the full system.

[Meta Claw @MetaClawdev]

https://t.co/OYn8QrDDNd

[Meta Claw @MetaClawdev]

Just talk to your agent it learns and EVOLVES. MetaClaw is an agent that meta-learns and evolves in the wild.

$META 0xe9ce29bbAa23185eAAdcDF30708A62B236082E22

https://t.co/wtFsaA0nqu

[Meta Claw @MetaClawdev]

I'm claiming my AI agent "MetaClaw" on @moltbook

Verification: coast-B1ZN

[Meta Claw @MetaClawdev]

Three Ways to Evolve
Choose the mode that fits your workflow. From lightweight skill injection to full reinforcement learning.

Skills Mode :
Lightweight proxy mode. Skills injected at every turn, auto-summarized after each session. No GPU required.

- Automatic skill injection
- Session summarization
- No GPU needed
- Works with any OpenAI-compatible API

RL Mode :
Continuous RL fine-tuning from live conversations. LoRA training with hot-swapped weights.

- Live conversation training
- LoRA fine-tuning
- Hot-swapped weights
- Tinker/MinT/Weaver support

Auto Mode
Smart scheduler defers weight updates to sleep/idle windows. Never interrupt active use.

- Smart scheduling
- Sleep hour updates
- Calendar integration
- Background optimization

0xe9ce29bbAa23185eAAdcDF30708A62B236082E22

https://t.co/wFrjFYi2co

[Meta Claw @MetaClawdev]

One-click OpenClaw plugin: MetaClaw now ships as a native OpenClaw extension — drop the folder into OpenClaw's extensions, run one command, and everything is set up automatically.

[Meta Claw @MetaClawdev]

Contexture layer: MetaClaw now persists cross-session memory for users and projects. Relevant facts, preferences, and project history are automatically retrieved and injected into prompts. Includes adaptive memory policy, background consolidation, and an optional memory sidecar service.

[Meta Claw @MetaClawdev]

Just talk to your agent it learns and EVOLVES. MetaClaw is an agent that meta-learns and evolves in the wild.

Growing Together
Join thousands of developers building the future of AI agents.

CA : 0xe9ce29bbAa23185eAAdcDF30708A62B236082E22

https://t.co/wtFsaA0nqu

[Meta Claw @MetaClawdev]

metaclaw setup # one-time config wizard metaclaw start # default: auto mode — skills + scheduled RL training
metaclaw start --mode rl # RL without scheduler (trains immediately on full batch) metaclaw start --mode skills_only # skills only, no RL (no Tinker needed)

0xe9ce29bbAa23185eAAdcDF30708A62B236082E22

https://t.co/wFrjFYi2co

[Meta Claw @MetaClawdev]

I just made a purchase from @dexscreener using @moonpay 🔥
https://t.co/oRdTG0loaw

[Meta Claw @MetaClawdev]

Introducing $META : MetaClaw is an open-source AI agent framework developed by AIMING Lab at the University of North Carolina at Chapel Hill. At its core, MetaClaw enables AI agents to achieve self-evolution and meta-learning by inserting a transparent proxy between users and large language models (LLMs). Every daily conversation becomes a learning signal, allowing agents to continuously improve during real-world deployment rather than relying solely on offline training.

Traditional reinforcement learning approaches require massive annotated datasets and expensive GPU clusters. MetaClaw eliminates these barriers. Through its innovative architecture, agents accumulate experience from real-time user interactions, automatically extract and inject new skills, and achieve continuous capability improvement — all without pre-built datasets or dedicated GPU infrastructure.

The MetaClaw framework combines online reinforcement learning, skill injection, and intelligent scheduling into a unified system, providing a fundamentally new paradigm for building adaptive, autonomous AI agents that grow smarter with every interaction.

CA : 0xe9ce29bbAa23185eAAdcDF30708A62B236082E22

web : https://t.co/wFrjFYi2co