InnerVault

Library

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

Results

  1. Multi-workspace profile router, MCP server isolation auditor, and CLAUDE.md <-> AGENTS.md instruction bridge for Claude Code and OpenAI Codex.

    Stale GitHub, Hung2124 93 ★MITUpdated 19 days ago

    git clone https://github.com/Hung2124/codex-multi-profile.git
  2. Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

    Stale GitHub, parcadei 3,944 ★MITUpdated 9 months ago

    git clone https://github.com/parcadei/Continuous-Claude-v3.git
  3. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

    Stale Agent skill collections on GitHub, obra MIT1 note

  4. skills

    Skills

    Agent skills and an AGENTS.md workflow template — isolate in worktrees, build to a service layer, prove with evidence, ship with before/after proof and Greptile review loops. For Claude Code, Cursor, and Codex.

    Stale GitHub, michaelshimeles 1,328 ★Updated 32 days ago

    git clone https://github.com/michaelshimeles/skills.git
  5. Self-hosted AI orchestrator for ticket-driven coding and automated code review in isolated containers.

    Stale GitHub, savoirfairelinux 9 ★GPL-3.0Updated 32 days ago

    git clone https://github.com/savoirfairelinux/virtual-engineer.git
  6. skills

    Skills

    Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.

    Stale GitHub, browser-act 6,329 ★MITUpdated 12 days ago

    git clone https://github.com/browser-act/skills.git
  7. vigilante

    Skills

    Vigilante is a sandbox-first orchestration layer for coding agents. It isolates every task in a git worktree, enforces strict credential scoping, and gives you full audit logs — so your agents can't burn down production.

    Indexed GitHub, aliengiraffe 41 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/aliengiraffe/vigilante.git
  8. OpenClaw GenPark Memory Vault - Cryptographically partitioned hierarchical memory vault with Ebbinghaus time-decay and HMAC namespace isolation.

    Stale GitHub, alphaparkinc 7 ★MITUpdated 16 days ago

    git clone https://github.com/alphaparkinc/openclaw-genpark-memory-vault.git
  9. Open-source guardrails between AI agents and FHIR clinical data — PHI redaction, immutable audit, step-up auth, tenant isolation. MCP server + OpenAI/Gemini adapters. A healthclaw.io project.

    Indexed GitHub, aks129 34 ★MITUpdated today

    git clone https://github.com/aks129/HealthClawGuardrails.git
  10. DeepSeek Harness plugin wrapping the upstream ppt-master skill set: byte-for-byte vendored skills, three lifecycle tools, optional venv interpreter isolation and a Plugins-page configuration card.

    Stale GitHub, SAXEM1997 7 ★MITUpdated 7 days ago

    git clone https://github.com/SAXEM1997/dsh-ppt-master-wrapper.git
  11. dely

    Skills

    Multi-harness control protocol that turns requests into approved design contracts, orchestrating isolated worker sessions for sequential implementation and independent code reviews under Orca supervision for Claude Code, Codex, Cursor, Antigravity, and other AI coding agents.

    Stale GitHub, hieuphung97 90 ★MITUpdated 12 days ago

    git clone https://github.com/hieuphung97/dely.git
  12. researchforge

    Skills

    A lab protocol for coding agents. Freeze baselines, run hypotheses in isolated worktrees, reject failures and validate improvements from Claude Code, Cursor or a direct API key (Gemini/Anthropic/openAI).

    Indexed GitHub, forger-labs-hq 9 ★Apache-2.0Updated yesterday

    git clone https://github.com/forger-labs-hq/researchforge.git

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.