Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
opensquilla
Agents & frameworksOpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density
git clone https://github.com/TokenRhythm/opensquilla.git -
tokenops
Agents & frameworksRun-aware token governance for multi-agent systems.
git clone https://github.com/theagentplane/tokenops.git -
syftr
Agents & frameworkssyftr is an agent optimizer that helps you find the best agentic workflows for your budget.
git clone https://github.com/datarobot/syftr.git -
awsl
Agents & frameworksCodex-verified, Claude-compatible durable local runtime for Claude Code Workflow JS, with resume, checkpoints, budgets, and Git worktrees
git clone https://github.com/XhinLiang/awsl.git -
ClaudeCode-Workflow-Lab
Agents & frameworksComplete Guide 2026: Claude Code Manual – Workflow Pipelines & Adversarial Budget Loops
git clone https://github.com/Frisher1/ClaudeCode-Workflow-Lab.git -
preference-lab
Agents & frameworksPolicy-driven preference data for content moderation, with source-linked evidence, resumable runs, budget controls and TRL/ShareGPT exports.
git clone https://github.com/dengxianghua888-ops/preference-lab.git -
Sovereign-OS
Agents & frameworksConstitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.
git clone https://github.com/Justin0504/Sovereign-OS.git -
willdeep-cli
Agents & frameworks自托管 AI Coding Agent(Rust):常驻 Runtime 撑起终端 / 浏览器 / 手机三端;每行改动可追溯到具体 Agent 与工具调用,子 Agent 的活由退出码裁决,检查点回退、目标 token 预算与验收清单跨轮次跨重启累计,用量与反馈账本留在本地。接任意 OpenAI 兼容或 Anthropic 端点。Self-hosted auditable AI coding agent: per-line attribution, exit-code-verified sub-agents, restart-safe goal budgets, local usage and feedback ledgers.
git clone https://github.com/niuwoai/willdeep-cli.git -
rikkahub-agent-pure
Agents & frameworksRikkaHub Agent · Pure — an Android AI agent that survives long runs. Independent hardening pass on the rikkahub on-device agent: usage ledger & budgets, on-demand tools, expert sub-agents, cold memory, chained workflows. Kotlin/Compose, Shizuku/Termux/MCP. QQ group 1030362371.
git clone https://github.com/wuyhong715/rikkahub-agent-pure.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.