Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Aegis
Agents & frameworksWindows-first desktop oversight for AI agents: live monitoring, local security reviews, token usage, audit reports and opt-in action policies/MCP gateways. Experimental Hyper-V guest execution; macOS/Linux experimental.
git clone https://github.com/antropos17/Aegis.git -
orloj
Agents & frameworksAn orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and governs them for production-grade operation.
git clone https://github.com/OrlojHQ/orloj.git -
prismor
Agents & frameworksSelf-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)
git clone https://github.com/PrismorSec/prismor.git -
open-managed-agents
Agents & frameworksOpenMA handles sessions, execution and recovery, so you can build and run agents with any model, any harness, any sandbox, on any cloud. An open-source, self-hostable alternative to Claude Managed Agents and OpenAI Agents API.
git clone https://github.com/openma-ai/open-managed-agents.git -
jarviscore-framework
Agents & frameworksJarvisCore is a runtime where AI agents operate as a fleet of equal peers. Agents discover one another by capability, execute tasks from a shared ledger, and authenticate to every external service through a zero-trust broker, never with their own keys.
git clone https://github.com/Prescott-Data/jarviscore-framework.git -
dsh-permission-rules
Agents & frameworksClaude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and workspace-path matching on the tools/pre-execute waterfall, session-log audit, and HMR reload.
git clone https://github.com/PerryLink/dsh-permission-rules.git -
openhermit
Agents & frameworksOpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you already use.
git clone https://github.com/HCF-STUDIOS/openhermit.git -
Varin
Agents & frameworksThe open-source agent harness, ready out of the box and customizable in depth. Tools, context, durable execution, permissions and recovery for code, research and office work, with a long-running super-agent Bot that leads a team of agents.
git clone https://github.com/Astrmira/Varin.git -
resp-warden-desk
Agents & frameworksAn eight-agent rule engine for on-chain risk analysis. Seven rules propose, one vetoes. Read-only, no keys, no execution.
git clone https://github.com/ElysiumduskImmortal63439/resp-warden-desk.git -
the-pair
Agents & frameworksOpen-source AI pair programming desktop app: a read-only Mentor and an Executor agent cross-check each other's code to catch AI mistakes before they land. Bring any model — Claude, GPT, Gemini, Kimi, GLM, Qwen or local Ollama. No agent CLI needed. macOS / Windows / Linux.
git clone https://github.com/timwuhaotian/the-pair.git -
Nosis
Agents & frameworksNosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
git clone https://github.com/EvannZhongg/Nosis.git -
mc_aiplayer
Agents & frameworksAutonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a real player to mine, build, farm, fight and survive from natural-language commands. LLM plans, deterministic tasks execute — no Python harness, no bot account.
git clone https://github.com/zoyluoblue/mc_aiplayer.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.