InnerVault

Library

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

Results

2,790 results Clear search and filters
  1. SWE-bench_Verified

    Datasets & benchmarks

    Hugging Face dataset by princeton-nlp

    Indexed Hugging Face Hub, princeton-nlp 411 ♥Updated 21 months ago

    princeton-nlp/SWE-bench_Verified
  2. Big-Math-RL-Verified

    Datasets & benchmarks

    Hugging Face dataset by SynthLabsAI

    Indexed Hugging Face Hub, SynthLabsAI 246 ♥apache-2.0Updated 20 months ago 1 note

    SynthLabsAI/Big-Math-RL-Verified
  3. CLM-v0.1-8B

    Models

    text ranking model by Contrastive-LM · contrastive-lm

    Stale Hugging Face Hub, Contrastive-LM 780 ♥apache-2.0Updated 53 days ago

    Contrastive-LM/CLM-v0.1-8B
  4. model by speechbrain · speechbrain

    Stale Hugging Face Hub, speechbrain 355 ♥apache-2.0Updated 21 months ago

    speechbrain/spkrec-ecapa-voxceleb
  5. SWE-bench_Verified

    Datasets & benchmarks

    Hugging Face dataset by SWE-bench

    Stale Hugging Face Hub, SWE-bench 188 ♥Updated 3 months ago

    SWE-bench/SWE-bench_Verified
  6. dapr-agents

    Agents & frameworks

    Build durable, autonomous, resilient and observable AI agents with built-in workflow orchestration, security, statefulness and telemetry.

    Stale GitHub, dapr 773 ★Apache-2.0Updated 6 days ago

    git clone https://github.com/dapr/dapr-agents.git
  7. nautilus-compass

    Datasets & benchmarks

    Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered criteria) — by Nautilus Platform

    Indexed GitHub, chunxiaoxx 1,258 ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/chunxiaoxx/nautilus-compass.git
  8. dsh-research-report

    Tools & apps

    Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

    Indexed GitHub, PerryLink 214 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/PerryLink/dsh-research-report.git
  9. Verovo

    Agents & frameworks

    AI financial audit and task economics: connect usage, supplier charges and business outcomes to calculate task costs, cost per verified success and ROI.

    Indexed GitHub, roy-tong 219 ★MITUpdated yesterday

    git clone https://github.com/roy-tong/Verovo.git
  10. Claude Code skills for journalism, media, and academia - verification, FOIA, data journalism, academic writing, and more

    Stale GitHub, jamditis 452 ★MITUpdated 4 days ago

    git clone https://github.com/jamditis/claude-skills-journalism.git
  11. korean-law-mcp

    MCP servers

    법령·판례를 AI가 찾고 인용까지 검증하는 MCP 서버 — 법제처 API 42개를 도구 10개로: 법령·조문·별표, 판례·헌재·해석례 23개 도메인, 조례 정비 레이더, 신구조문대비표 | MCP server for Korean law — statutes, precedents, ordinances, comparison tables and citation verification

    Indexed GitHub, chrisryugj 2,879 ★MITUpdated today

    git clone https://github.com/chrisryugj/korean-law-mcp.git
  12. TLA+ model checking and Lean proofs for coding agents, with explicit tool setup.

    Indexed GitHub, michael-denyer 45 ★GPL-3.0Updated 3 days ago

    git clone https://github.com/michael-denyer/agent-formal-verify.git
  13. ScienceClaw

    AI repositories

    Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.

    Stale GitHub, beita6969 1,022 ★MITUpdated 16 days ago

    git clone https://github.com/beita6969/ScienceClaw.git
  14. Best AI Coding Workflow Plugin Pipeline 2026

    Indexed GitHub, aufamubarak 114 ★Updated yesterday

    git clone https://github.com/aufamubarak/plan-execute-verify-claude-code.git
  15. skills

    Skills

    Agent skills to find and fix software bugs

    Stale GitHub, workersio 204 ★MITUpdated 3 months ago

    git clone https://github.com/workersio/skills.git
  16. Linghun

    Tools & apps

    AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

    Indexed GitHub, linghungegeg 475 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/linghungegeg/Linghun.git
  17. opendraft

    Agents & frameworks

    The open-source agent system that writes research papers with verified citations. Every citation checked against Crossref, OpenAlex and Semantic Scholar.

    Stale GitHub, federicodeponte 524 ★MITUpdated 12 days ago

    git clone https://github.com/federicodeponte/opendraft.git
  18. open-ontologies

    MCP servers

    Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.

    Indexed GitHub, fabio-rovai 2,903 ★MITUpdated yesterday

    git clone https://github.com/fabio-rovai/open-ontologies.git
  19. Meta_Kim

    Agents & frameworks

    Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.

    Stale GitHub, KimYx0207 288 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/KimYx0207/Meta_Kim.git
  20. deepdive

    Prompts

    Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

    Indexed GitHub, Socialpranker 371 ★MITUpdated yesterday

    git clone https://github.com/Socialpranker/deepdive.git
  21. mathema

    MCP servers

    Claim-Driven Development: turn software intent into verifiable evidence.

    Stale GitHub, tetrionlabs 169 ★Custom licence (see repository)Updated 5 days ago

    git clone https://github.com/tetrionlabs/mathema.git
  22. emilia-protocol

    MCP servers

    Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

    Stale GitHub, emiliaprotocol 550 ★Apache-2.0Updated 4 days ago

    git clone https://github.com/emiliaprotocol/emilia-protocol.git
  23. python

    Agents & frameworks

    Open-source Python challenge courses — your AI coding agent teaches, verify.py decides when you're done.

    Stale GitHub, flypythoncom 4,182 ★Custom licence (see repository)Updated 12 days ago

    git clone https://github.com/flypythoncom/python.git
  24. Reticle

    MCP servers

    Verify a running web app from the inside over MCP: look, act, observe, assert. No screenshots.

    Indexed Official MCP Registry, io.github.reticlehq 1,279 ★Updated yesterday 1 note

    @reticlehq/server@3.10.6

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.