Indie software from github
-
arxiv-reader-mcp
Search and extract research papers from arXiv using this Model Context Protocol server.
-
tokenctl
Hierarchical org→team→dev token-budget proxy for LLM traffic: meter, soft-throttle, hard-deny, and in-flight preemption across providers on one shared wallet.
-
awesome-codex-pets
Browse and install over 174 animated pets for the OpenAI Codex CLI using this community-curated collection.
-
node-scorecard
Network intelligence & historical diagnostics for Sentinel dVPN nodes. Reliability scores, lease tracking, "where to host" advisor — no backend, fully static, archived on Walrus.
-
ClAudit
Catch false-positive Claude Code safety/policy blocks, scrub PII, and auto-file clean GitHub issues. FOSS.
-
skill-vault
Organize, secure, and find Claude Code skills in one vault for easy reuse
-
terminal-fish
Catch, collect, and display virtual fish in your terminal with this Python and Bash gaming suite.
-
tailor
TAILOR — self-hosted AI memory framework. 100% local, LLM-agnostic, MCP-native
-
Plumb
-
Mustatil-YOLO-AI-Model-Trainer-
An AI trainer. Detect whatever you want on maps at GIS-level standards. Archeology tool for fast detection of archeological sites with Yolo AI. For archeology and GIS tasks. Geospatial AI Workspace for annotation, training, detection and visual pipelines.
-
Repo2AI
Convert code repositories into structured, size-limited context packs for AI tools like ChatGPT, Claude, and Cursor.
-
Do-SOUL-Alaya
The local-first memory plane for CLI coding agents. Codex and Claude Code attach via MCP; SQLite-backed, evidence-gated, no GUI. Cross-session memory that the agent proposes and a governance gate decides.
-
wizard
Self-extending autonomous agent in one Rust binary. One-line install, any provider (OpenAI-compatible, Anthropic, xAI) or fully local via llama.cpp, live /evolve self-modification, MCP, messaging gateway, built-in bench
-
jinguyuan-dumpling-skill
Connect your AI assistant to Jinguyuan Dumpling Restaurant data to query store information, check operating hours, and manage queue numbers via MCP.
-
kry
Tamper-evident, stranger-verifiable receipts for LLM cost-savings — anyone can recompute your caching/routing savings math offline, no trust in your dashboard required. Pure stdlib, zero-dependency.
-
thingctx
Drive any agent against any W3C WoT Thing from its description. No per-integration server.
-
Lumi_Agent
Production-ready autonomous AI agent for software engineering, featuring planning, coding, memory, and continuous self-improvement. OPEN SOURCE.
-
edgeever
Self-hosted, Cloudflare-native Evernote alternative with REST API, MCP, and PWA support.
-
context-bridge-mcp
A local-first code retrieval MCP server for AI coding agents. Hybrid keyword + vector search over Graphify-indexed codebases, with domain-aware ranking profiles.
-
centrs
Multi-protocol (REST, native API, mac-telnet, SSH) CLI and TypeScript interface to RouterOS, with rich help and validation
-
tinkering
Small AI-assisted operator tools, released as I build them. Starting with a LinkedIn engagement console that drafts grounded comments instead of generic ones.
-
research-repo-doctor
Artifact Evaluation readiness checker for research code: static scan, safe fixes, verify ladder, appendix, and agent-ready gates. Local-first, no API key.
-
tezgah
Build production-ready SaaS apps with Claude Code and Tezgah, covering auth, payments, email, compliance, testing, analytics, and deployment
-
sophia-agi
Wisdom before intelligence. A provenance-aware reasoning layer that abstains instead of fabricating — stops LLMs inventing attributions and merging distinct traditions. Measured: 0% fabrication on unknown-answer traps (vs 17–25% raw); −12.5pt hallucinated attributions at 0% false-positive cost. An AGI-candidate proof package, not proven AGI.
-
litmux
Build unit tests for AI prompts to compare models, track performance, and prevent regressions.
-
hugrs
Unified model weight mirror service for Hugging Face and ModelScope with shared, compressed chunk storage for efficient AI model hosting and distribution. 共享压缩分块的hf/ms统一镜像服务.
-
transitrix-studio
VS Code + IntelliJ IDEA extension for editing and previewing Transitrix diagrams — BPMN, Goals, DGCA, capability maps. Text-first; live preview as you type. MIT licensed.
-
Opptrix
Opptrix — 大模型驱动的投研助手 | Open-source LLM research assistant for China A-shares. 40+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.
-
spyc
A Rust TUI file commander where the AI agent in the side pane can query the file commander itself
-
trusca
Self-hosted, open-source SCA portal — vulnerability (CVE), license compliance, and SBOM management in one UI. Black Duck/Snyk-class capabilities, Apache-2.0.
-
fin
a neon-electric TUI Jellyfin & Subsonic client - powered by Symphonia, mpv, Chromecast & UPnP MediaRenderer
-
stelekit
Local-first outliner and PKM app — plain markdown on your disk, native on every platform
-
ClaudeCode-Model-Rotator
Connect Claude Code to local Ollama models and OpenRouter via a dynamic proxy to bypass ecosystem locks and use free APIs.
-
selfhost.directory
A searchable directory of 2,700+ self-hosted, open-source apps — with setup guides, alternatives & live version tracking.
-
react-native-auditor
A local-first React Native & Expo project auditor for release readiness, dependency health, and risk reports.
-
reyn
AI agent workflow OS . Constrained, validated, replayable execution. Predictability over autonomy.
-
auxly-memory-cli
A local-first, file-based memory CLI for AI tools. Own your context in plain Markdown — auditable, versionable, and provider-agnostic.
-
nothumansearch
Search engine for AI agents — ranks sites by agentic readiness (llms.txt, OpenAPI, MCP, ai-plugin). MCP server, REST API, full-text search. 8,000+ indexed sites.
-
personal-memory-bank
AI session memory framework for Claude Code and Cursor. Five structured files, the mb CLI (13 commands, 24 health checks), versioned git hooks, CI guardrails, semantic drift detection, and slash commands for code review, security scanning, and test coverage. Drop-in install for any project.
-
prozetta
LLM pipeline for literary translation with a consistency glossary and a self-checking quality loop
-
claudegram
Connect your personal Telegram account to Claude Code using the MTProto protocol instead of the Bot API.
-
ophel-docs
Document for Ophel Atlas.
-
owl-terminus
Owl AI Terminal Companion 2026 - Best Free AI Coding Assistant Download
-
clauth
Claude Code account switcher, real-time usage monitor with a CLI, TUI and MCP
-
ai-cost-optimzer
Monitor, analyze, and optimize your LLM API spending across providers
-
marginalia
Kindle Scribe handwritten notebooks -> Obsidian Markdown, with OCR and human review.
-
xge
XGE is a work‑in‑progress C++20 engine exploring modern engine architecture: reflection‑driven data, platform‑agnostic core, modular renderer backends (DX12 + Vulkan planned), and a dual‑runtime scripting model using CoreCLR for the editor and NativeAOT for runtime builds. Focused on clean systems engineering, not commercial features.
-
Jarvis-AI
Automate desktop tasks and control your computer using simple voice commands with this Python-based personal assistant.
-
claude-code-manager
Claude Code Manager - sessions, MCP, skills, usage & accounts in your VS Code sidebar. 100% local.
-
Roamarr
The private, self-hosted travel organizer for every moving part of a trip. Track flights, stays, documents, companions, reminders, expenses, and sharing in one itinerary hub - all powered by SvelteKit and MongrelDB.
-
compass
Product development framework for AI-assisted teams. Bets, roles, decisions — all in markdown
-
claudian
Integrate AI coding agents directly into your Obsidian sidebar to manage projects and automate workflows with Claude and Codex models.
-
V.O.I.D-VPN_Bypass
Сборник ссылок с конфигами Vless для обхода блокировок и белых списков в Российской Федерации by V.O.I.D™
-
voidly-pay
Off-chain credit ledger + hire marketplace for AI agents. Ed25519-signed envelopes, atomic settlement, hire-and-release escrow. https://voidly.ai/pay
-
Yggdrasil
Durable, local-first memory for AI coding agents over MCP — zero-dependency, curated & semantically de-duped, you own the data (SQLite + Markdown). Works with Claude Code, Codex & any MCP host.
-
vonzio
The runtime for production agents — bring your own model. Open-source, self-hostable, isolated Docker workspaces per session.
-
dxkit
Deterministic Stop-gate and code-graph context for AI coding agents: blocks only net-new findings and gives the loop a structural map of the codebase, locally, with no model in the gate.
-
claude-toolkit
Small, honest Claude Code tools for the CLI and desktop app. /handoff mirrors your current session into a fresh one (same model, effort and permissions). /route sends delegated work down to the cheapest capable model, keeps judgment and review on yours, and reports the savings against honest baselines.
-
power-framework
P.O.W.E.R. - Hybrid Knowledge Management Framework (P.A.R.A. + OKF Overlay + LLM-Wiki + Execution Rules)
-
ClawUI
Run a cross-platform OpenClaw desktop client with built-in Gateway, onboarding, chat, and a full admin panel.