Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
aizen
Agents & frameworksAizen is an AI coding agent that lives on your PC or VPS. Control it from your phone while it autonomously fixes code, runs tests, and reports the results back to you.
git clone https://github.com/talmetis-labs/aizen.git -
LoomFlow
Tools & appsLightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, publish it as an API. One-command Docker self-hosting. Open-source alternative to Dify / n8n.
git clone https://github.com/banmu123/LoomFlow.git -
kali-mcp-go
MCP serversMCP runtime for AI-assisted security testing with Kali tools, explicit target controls, bounded scanning, structured evidence, and persistent Docker deployment.
git clone https://github.com/found-cake/kali-mcp-go.git -
kiso
Agents & frameworksThe durable runtime for AI agents: event-sourced sessions, approvals that persist across processes, exact resume after a crash. A 2,200-line TypeScript kernel, and kiso-code, the coding agent built on it.
git clone https://github.com/vincemakes/kiso.git -
reevesagents
Agents & frameworksRun Claude Code, Codex, Kimi, OpenCode, Hermes and 20 other coding agents side by side, from the CLI, TUI, Web UI or MCP.
git clone https://github.com/mertkayacs/reevesagents.git -
Claude Fable 5.1
ModelsThe hardest reasoning and long-running work: multi-step decisions and projects that run for hours.
-
cinch
MCP serversRun AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.
@cinch-codes/mcp@0.1.1 -
Inngest MCP by usefulapi
MCP serversTrace events to function runs to the failing step, and bulk-cancel runs.
-
OTInstaller
MCP serversInstall and run open-source OSINT tools in a local sandbox, asking before runs that touch a target.
https://github.com/OTInstaller/ot/releases/download/v0.16.1/ot_0.16.1_darwin_amd64.mcpb@0.16.1 -
evalpair
MCP serversRun LLM eval suites on local or hosted models; compare runs with intervals and a noise floor.
evalpair@0.1.1 -
Koschei
MCP serversRun agent-written code under a capability policy: see what a program can touch before it runs.
koschei-lang@0.14.0 -
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 -
open-tabletop-gm
Agents & frameworksLLM-agnostic tabletop RPG Game Master framework. Runs on OpenCode, LM Studio, or any LLM service. D&D 5e included as reference system — add any TTRPG via a system module.
git clone https://github.com/Bobby-Gray/open-tabletop-gm.git -
mcp
MCP serversRunSec MCP server for workspace security scanning and remediation workflows.
@runsec/mcp@1.0.127 -
troupe
Agents & frameworksRun a team of coding agents you can actually watch: one approved plan, each role in its own tmux window and git worktree, on Claude Code or Codex.
git clone https://github.com/hitianqi/troupe.git -
xorcise
Datasets & benchmarksRun cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the claim.
git clone https://github.com/xorcise-ai/xorcise.git -
claude-overlay
Tools & appsA floating, screen-aware Claude Code chat for Windows - it reads your screen to answer, and runs on your own Claude (And Codex btw) subscription (no API key).
git clone https://github.com/shengyanlin/claude-overlay.git -
cc-fleet
Skills🚢 Run Claude Code's ⚙️ Dynamic Workflows, 👥 Agent Teams & ⚡ Subagents on any third-party model — DeepSeek · GLM · Kimi · Qwen … or your Codex subscription. No Anthropic subscription needed. | 🚢 让 Claude Code 的 ⚙️ Dynamic Workflow、👥 Agent Team、⚡ Subagent 用上任意第三方模型 — DeepSeek · GLM · Kimi · Qwen…… 或你的 Codex 订阅,无需 Claude 订阅
git clone https://github.com/ethanhq/cc-fleet.git -
awesome-jev
Agents & frameworksLaunch what you built on Jev, TypeSafe AI's System One decision model: a weekly board where makers launch and people vote, over an index of public Jev examples by decision pattern, with source citations, dated link checks and call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema, platform matrix.
git clone https://github.com/kydlikebtc/awesome-jev.git -
inference.sh
MCP serversrun any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.
-
Pipe2.ai
MCP serversRun multi-step AI pipelines for video, image, audio and text: upload media, run, poll results.
-
ChargerDojo
MCP serversOCPI versions, checks and payload validation, plus your own test runs and run starts with a key.
-
AgentGo
MCP serversRun Codex and Claude Code on your computer from an MCP client, and track or continue their runs.
agentgo-mcp@0.3.1 -
Grok Build
MCP serversRun the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.
grok-build-mcp-server@0.2.5
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.