InnerVault

Library

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

Results

  1. alignment-handbook

    AI repositories

    Robust recipes to align language models with human and AI preferences

    Stale GitHub, huggingface 5,695 ★Apache-2.0Updated 54 days ago

    git clone https://github.com/huggingface/alignment-handbook.git
  2. alignfirst

    Skills

    Software engineering tools built for 2026.

    Stale GitHub, paleo 89 ★CC0-1.0Updated 16 days ago

    git clone https://github.com/paleo/alignfirst.git
  3. hands-on-modern-rl

    Docs & tutorials

    🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

    Stale GitHub, walkinglabs 4,769 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/walkinglabs/hands-on-modern-rl.git
  4. Arete-27B

    Models

    text generation model by NousResearch

    Indexed Hugging Face Hub, NousResearch 630 ♥apache-2.0Updated 10 days ago

    NousResearch/Arete-27B
  5. parlant

    Agents & frameworks

    Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

    Stale GitHub, emcie-co 18.3k ★Apache-2.0Updated 4 months ago

    git clone https://github.com/emcie-co/parlant.git
  6. AISafetyHot

    MCP servers

    AI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.

    Indexed GitHub, wuyoscar 2,127 ★Custom licence (see repository)Updated today

    git clone https://github.com/wuyoscar/AISafetyHot.git
  7. HRM-Text-1B

    Models

    text generation model by sapientinc · transformers

    Stale Hugging Face Hub, sapientinc 834 ♥apache-2.0Updated 2 months ago

    sapientinc/HRM-Text-1B
  8. PromptInject

    Prompts

    PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

    Stale GitHub, agencyenterprise 528 ★MITUpdated 6 months ago

    git clone https://github.com/agencyenterprise/PromptInject.git
  9. text generation model by AI-MO · transformers

    Stale Hugging Face Hub, AI-MO 352 ♥apache-2.0Updated 2 years ago

    AI-MO/NuminaMath-7B-TIR
  10. OpenJudge

    Skills

    OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

    Indexed GitHub, agentscope-ai 1,108 ★Apache-2.0Updated today

    git clone https://github.com/agentscope-ai/OpenJudge.git
  11. autoguardrails

    Datasets & benchmarks

    Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

    Stale GitHub, SantanderAI 129 ★Apache-2.0Updated 46 days ago

    git clone https://github.com/SantanderAI/autoguardrails.git
  12. Awesome-LLM-in-Social-Science

    Agents & frameworks

    Awesome papers involving LLMs in Social Science.

    Indexed GitHub, ValueByte-AI 653 ★MITUpdated 2 days ago

    git clone https://github.com/ValueByte-AI/Awesome-LLM-in-Social-Science.git
  13. motif

    MCP servers

    An AI-native molecular biology workbench for Claude Science: Claude opens sequence files and prepares analyses on request; you annotate, align, and review them in an interactive workspace.

    Stale GitHub, jvogan 47 ★MITUpdated 29 days ago

    git clone https://github.com/jvogan/motif.git
  14. Rules.txt

    Prompts

    LLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases

    Stale GitHub, Xayan 108 ★Custom licence (see repository)Updated 3 months ago

    git clone https://github.com/Xayan/Rules.txt.git
  15. text generation model by OBLITERATUS · transformers

    Stale Hugging Face Hub, OBLITERATUS 472 ♥gemmaUpdated 5 months ago

    OBLITERATUS/Gemma-4-12B-OBLITERATED
  16. Satori-Aligner

    MCP servers

    Factual alignment and semantic bias scanner for LLM inputs.

    Stale Official MCP Registry, io.github.Evozim Updated 5 months ago 1 note

  17. Premium agentic endpoint for cross-modal-embedding-aligner-mcp.

    Stale Official MCP Registry, io.github.Evozim Updated 3 months ago 1 note

  18. word-aligner

    MCP servers

    Turn a phrase and its translation into a shareable word-alignment diagram.

    Stale Official MCP Registry, io.github.tinygodsdev Updated 4 months ago 1 note

  19. Align

    MCP servers

    Cross-border payment lookups: USDT/USDC rates, off-ramp plans, network fees, IBAN checks, holidays

    Stale Official MCP Registry, dev.alignlabs Updated 3 days ago 1 note

  20. Check whether a NAICS code aligns with a vertical: a routing-for-review signal, not a determination.

    Stale Official MCP Registry, com.bonissystems Updated 4 months ago 1 note

  21. dsh-anchored-standard

    Agents & frameworks

    Two-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)

    Stale GitHub, xiaobright 3,741 ★Custom licence (see repository)Updated 26 days ago

    git clone https://github.com/xiaobright/dsh-anchored-standard.git
  22. Start private 1-on-1 or 3+ anonymous alignment rooms in 100+ languages (zero PII exposed).

    Indexed Official MCP Registry, io.iresolve.app Updated yesterday 1 note

  23. Align

    MCP servers

    Ask what your team decided in meetings, get your standup, and update Jira/Linear-synced tasks.

    Stale Official MCP Registry, com.meet-align Updated 17 days ago 1 note

  24. ALIGN

    MCP servers

    Your team's confirmed decisions, with receipts, for every coding agent (local stdio server).

    Stale Official MCP Registry, io.github.bharatreachdsp Updated 10 days ago 1 note

    @align-agent/cli@0.1.7

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.