AI — independent software & tools
-
travel-OS
TravelOS AI — Sistema Operativo Inteligente para Agencias de Viajes (Proyecto Integrador 2 EAFIT)
-
termina
Hybrid coding cockpit: the real pi TUI in a terminal with a live Monaco IDE — Change Review, Verify & Iterate, worldline candidate forks, and challenge mode.
-
tally
macOS menu bar AI usage monitor for multiple Claude and Codex accounts: quota, rate limits, and a smart launcher for Claude Code.
-
memory-seed
Portable local memory system and MCP search tooling for file-reading AI coding agents.
-
quireink
A self-hosted blog platform an AI agent can run for you. One Bun process, two SQLite files, no cloud account anywhere in the path.
-
quireink
A self-hosted blog platform an AI agent can run for you. One Bun process, two SQLite files, no cloud account anywhere in the path.
-
boardwire-ai
Autonomous AI news channel for builders. Boardwire reads the firehose, filters the hype, and ships only concrete updates teams can act on today.
-
neuralvault
Self-hosted AI memory and knowledge platform for contextual retrieval. Hybrid semantic + keyword search powered by Qdrant and PostgreSQL, with multi-workspace support and BYOK multi-provider flexibility.
-
copicu
Local-first clipboard workbench for search, scripts, and AI-assisted workflows.
-
gittensory
Backend intelligence and MCP tooling for Gittensor contributors and maintainers.
-
agent-profile
Configure Codex, Claude, and Tabnine to understand your project, follow its workflow, and respect its safety rules.
-
tokenix
Local semantic search, symbol graphs, secrets scanning, output filters, and CLI hooks that save 60-90% LLM tokens.
-
goguma
Wakes your Mac for scheduled jobs, holds it awake while long work finishes, and lets it sleep otherwise. Finds the cron jobs that have been missing runs; keeps a coding agent running with the lid shut.
-
vogon-runtime
Vogon Runtime is a Rust toolkit for deterministic, replayable AI workflows: structured prompts, provider-agnostic adapters, reproducible runs, and verifiable replay logs.
-
sdkproof
Type-check how well AI coding agents use your SDK's current API.
-
ai-code-reviewer
🔍 AI-powered automated code review tool that analyzes syntax, performance bottlenecks, and security flaws in pull requests.
-
flue
terminal multiplexer in the browser accessible from any device you own.
-
obsidian-skills
Use Agent Skills in Obsidian for Claude Code, Codex CLI, and other compatible agents
-
mnemos
Self-hosted memory + evidence layer for AI agents (Claude Code, Codex, Hermes, ...) — embeddable Go library, MCP / HTTP / CLI, evidence-backed claims, bitemporal recall, axi-go execution kernel with JSONL audit + token budgets, cosign-signed releases with SLSA L3 provenance. No vendor cloud, no per-call billing.
-
wigolo
The go-to web for your agent!
-
kotro-proxy-engine
Local AI/LLM proxy with semantic caching, MCP injection scanning, cost budgeting, and intelligent model routing — Rust/Axum
-
kprompt
The AI Runtime for Kubernetes
-
ai-intel
A self-writing AI intel wiki — Claude routines write twice-daily briefs to a markdown vault, with ntfy alerts, CI health checks, and a desktop reader (dashboard · graph · files).
-
ai-intel
A self-writing AI intel wiki — Claude routines write twice-daily briefs to a markdown vault, with ntfy alerts, CI health checks, a mobile-optimized hosted web app, and a desktop reader (dashboard · graph · files).
-
awesome-android-app-repositories
⚡ Curated & continuously updated catalog of 1,600+ open-source Android apps, GitHub repositories, developer tools, AI platforms, and utilities automatically synchronized from Telegram.
-
git-commit
AI-powered git commit workflow assistant using Google Gemini. Zero-dependency Python CLI that generates conventional commit messages, bumps semantic versions, tags and updates changelogs, automating the commit → push → PR → CI lifecycle. Interactive staging, amend modes, session recovery, and CI/CD non-interactive mode.
-
cli
-
MailFathom
A brain for your mail: MailFathom turns IMAP mailboxes into a self-hosted, AI-native service. Mail synchronizes into your own PostgreSQL, is indexed for search and retrieval, and is served to AI agents over the Model Context Protocol. Read-only today; semantic retrieval, answering, and gated write tools next. .NET 10, Apache-2.0.
-
kujo
Kujo is the programming language for AI-native software
-
servio-social
AI-powered social media content automation for Servio — GitHub Actions + Claude
-
everlingo
An AI language companion with memory. EverLingo captures your learning context as you learn. When you look up a word, translate a sentence, or ask a question, Nori 🐹 turns the moment into a useful note. Later, it recalls relevant notes to help strengthen your memory.
-
kilo-pulse
Best Free Kilo Agentic Engineering Platform Guide 2026 - Ship Code Faster Now
-
MonoLine
An automated Python script that dynamically updates my GitHub Profile README using Google Gemini AI.
-
achuk
Achuk (अचूक, 'infallible') — an AI-first programming language where generated code can't be fake. Grammar-constrained, compiler-verified, ships its own model.
-
claw
The programming language where AI can't hallucinate APIs — ungeneratable, not just discouraged.
-
autodoc-ai
Generate OpenAPI 3.0 docs from Python code with Gemini AI for fast, structured API documentation
-
DecisionNode
Store and query shared structured memory across Claude Code, Cursor, Windsurf, and any MCP client with a local CLI and MCP server
-
awesome-persona-skills
Distill human behaviors, roles, and personality traits into reusable AI agent skills for your projects.
-
forgeterm
Monitor AI coding agents in real-time to block unauthorized file access, network connections, and dangerous commands while enforcing system resource limits.
-
CrewLoop
A team of specialized AI agents covering the complete software development flow — from requirements discovery to deploy. One responsibility per agent, specs as source of truth, no shortcuts.
-
picamd
Edit Markdown with a native macOS AppKit editor featuring inline WYSIWYG rendering and direct file access without library databases.
-
Lians
Agent memory for regulated environments. Bitemporal model, tamper-evident audit chain, GDPR crypto-shred.
-
python-sdk
Integrate the Assinafy API into your Python applications to manage electronic signatures, documents, and webhooks with a synchronous client.
-
xharness
🤝 装在你电脑上的 AI 编程搭档（macOS GUI + CLI）：把项目文件夹丢给它，用聊天布置任务——自动读代码、改代码、跑命令验证，全程可见。支持 DeepSeek / Kimi / 任意 Anthropic 兼容模型；截图粘贴看图干活；技能系统；数据全本地。
-
llm-price-tracker
A daily-updated reference of LLM model pricing across all major providers (OpenAI, Anthropic, Google, Mistral, and more)
-
llm-systems-manager
LLM Systems Manager — real-time observability and control for LLM systems
-
repo-confidence
AI agent skills and evidence-backed workflows for understanding unfamiliar codebases, assessing change impact, and growing developers into confident maintainers.
-
LogCoreOS
Self-hosted AI life OS — private AI with persistent memory, tasks, calendar, household & team sharing, n8n automations. Your AI. Your data. Your server.
-
quantum-hardware-mcp
Open-source MCP server giving AI assistants live, natural-language control of real quantum hardware across IBM Quantum, IonQ, and AWS Braket
-
Fortnite-Aim-NewEraAI-Assist
Advanced Computer Vision & Input Optimization Framework for Fortnite Environments
-
agent-harness-orchestrator
Agent Orchestrator 2026: AI-Powered Multi-Repo Task Runner & Automation Hub
-
wechat-opencode
Bridge WeChat to local OpenCode for chat, permission approvals, slash commands, and session persistence on macOS and Linux
-
sage
GraphRAG Lore & World-Building System
-
code-by-wire
The cockpit for local Claude Code.
-
LMcode-cli
A terminal-native AI coding agent — a fast, scriptable TUI CLI for builders.
-
ai-hiring-workflow-engine
Analyze resumes against job descriptions using Claude AI to generate match scores, gap insights, and improvement actions for recruiters and job seekers.
-
pipe
Pipe (SPR) — Semantic Pipeline Runtime: A language where AI operations are primitives
-
followme
Automated GitHub repo discovery, NVIDIA NIM LLM grading, and auto follow/star — Node.js worker on Render + Next.js dashboard on Vercel
-
Lattice_release
Manage academic references on macOS with a native Swift literature manager built for speed and a clean workflow
-
raphael
A learning layer (brain) for AI coding agents — distills lessons from your real projects and injects them back at the right moment. Local-first, human-gated, measured.