InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. WebCanvas

    Agents & frameworks

    All-in-one Web Agent framework for post-training. Start building with a few clicks!

    Stale GitHub, iMeanAI 281 ★MITUpdated 16 months ago

    git clone https://github.com/iMeanAI/WebCanvas.git
  2. UltraData-SFT-Agent-2609

    Datasets & benchmarks

    Hugging Face dataset by openbmb

    Indexed Hugging Face Hub, openbmb 322 ♥apache-2.0Updated 2 months ago

    openbmb/UltraData-SFT-Agent-2609
  3. curator

    AI repositories

    Synthetic data curation for post-training and structured data extraction

    Stale GitHub, bespokelabsai 1,751 ★Apache-2.0Updated 22 days ago

    git clone https://github.com/bespokelabsai/curator.git
  4. agent-apprenticeship

    Agents & frameworks

    The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

    Stale GitHub, ray-r-ren 1,616 ★MITUpdated 37 days ago

    git clone https://github.com/ray-r-ren/agent-apprenticeship.git
  5. CaPtain

    Agents & frameworks

    CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents — CaPtain-Harness, SFT and RL training code, benchmark adapters

    Indexed GitHub, waltstephen 96 ★MITUpdated 6 days ago

    git clone https://github.com/waltstephen/CaPtain.git
  6. Grepped marketplace

    MCP servers

    Real company data for AI post-training, evals and RL environments, for qualified buyers.

    Stale Official MCP Registry, ai.grepped Updated 9 days ago 1 note

  7. A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

    Indexed OpenRouter model list, liquid Updated 10 days ago

    liquid/lfm-3-1.7b
  8. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

    Indexed OpenRouter model list, deepseek Updated 3 months ago

    deepseek/deepseek-v4-flash-0731
  9. A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used...

    Indexed OpenRouter model list, liquid Updated 10 days ago

    liquid/lfm-3-1.7b:free
  10. DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....

    Indexed OpenRouter model list, deepseek Updated 3 months ago

    deepseek/deepseek-v4-flash-0731:batch
  11. Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...

    Indexed OpenRouter model list, particle-ai Updated 19 days ago

    particle-ai/particle-1
  12. Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...

    Indexed OpenRouter model list, particle-ai Updated 19 days ago

    particle-ai/particle-1:free
  13. Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

    Indexed OpenRouter model list, moonshotai Updated 24 days ago

    moonshotai/kimi-k3.1-pro
  14. Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...

    Indexed OpenRouter model list, moonshotai Updated 24 days ago

    moonshotai/kimi-k3.1-pro:batch
  15. GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...

    Indexed OpenRouter model list, z-ai Updated 14 days ago

    z-ai/glm-5.3-flashx-legal

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.