Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
alignment-handbook
AI repositoriesRobust recipes to align language models with human and AI preferences
git clone https://github.com/huggingface/alignment-handbook.git -
alignfirst
SkillsSoftware engineering tools built for 2026.
git clone https://github.com/paleo/alignfirst.git -
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.
git clone https://github.com/walkinglabs/hands-on-modern-rl.git -
Arete-27B
Modelstext generation model by NousResearch
NousResearch/Arete-27B -
parlant
Agents & frameworksBuild reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
git clone https://github.com/emcie-co/parlant.git -
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git -
HRM-Text-1B
Modelstext generation model by sapientinc · transformers
sapientinc/HRM-Text-1B -
PromptInject
PromptsPromptInject 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
git clone https://github.com/agencyenterprise/PromptInject.git -
NuminaMath-7B-TIR
Modelstext generation model by AI-MO · transformers
AI-MO/NuminaMath-7B-TIR -
OpenJudge
SkillsOpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
git clone https://github.com/agentscope-ai/OpenJudge.git -
autoguardrails
Datasets & benchmarksAlignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
git clone https://github.com/SantanderAI/autoguardrails.git -
Awesome-LLM-in-Social-Science
Agents & frameworksAwesome papers involving LLMs in Social Science.
git clone https://github.com/ValueByte-AI/Awesome-LLM-in-Social-Science.git -
motif
MCP serversAn 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.
git clone https://github.com/jvogan/motif.git -
Rules.txt
PromptsLLM alignment jailbreak; a set of instructions for auditing their internal reasoning and uncovering biases
git clone https://github.com/Xayan/Rules.txt.git -
Gemma-4-12B-OBLITERATED
Modelstext generation model by OBLITERATUS · transformers
OBLITERATUS/Gemma-4-12B-OBLITERATED -
Satori-Aligner
MCP serversFactual alignment and semantic bias scanner for LLM inputs.
-
Execute cross-modal-embedding-aligner-mcp
MCP serversPremium agentic endpoint for cross-modal-embedding-aligner-mcp.
-
word-aligner
MCP serversTurn a phrase and its translation into a shareable word-alignment diagram.
-
Align
MCP serversCross-border payment lookups: USDT/USDC rates, off-ramp plans, network fees, IBAN checks, holidays
-
Compliance Batch Alignment
MCP serversCheck whether a NAICS code aligns with a vertical: a routing-for-review signal, not a determination.
-
dsh-anchored-standard
Agents & frameworksTwo-phase DeepSeek Harness preset: Minimal-aligned bootstrap, then full Standard tools (Project2 98/99)
git clone https://github.com/xiaobright/dsh-anchored-standard.git -
iResolve Private Alignment Rooms
MCP serversStart private 1-on-1 or 3+ anonymous alignment rooms in 100+ languages (zero PII exposed).
-
Align
MCP serversAsk what your team decided in meetings, get your standup, and update Jira/Linear-synced tasks.
-
ALIGN
MCP serversYour team's confirmed decisions, with receipts, for every coding agent (local stdio server).
@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.