llm — independent software & tools
-
claude-minder
MemPenny Plus: Claude Memory Manager 2026 - Lean AI Companion Sync & Rollback Tool
-
agentty
AI pair programming in your terminal — one static binary, sub-ms startup, any model
-
cast
Minimal terminal coding agent with OpenAI-compatible routing. Works with any provider — OpenRouter, Ollama, vLLM, LiteLLM, or your own.
-
cast
Minimal terminal coding agent with OpenAI-compatible routing. Works with any provider — OpenRouter, Ollama, vLLM, LiteLLM, or your own.
-
awesome-pi-agent-practices
Bilingual, evidence-led, reproducible practices for the Pi coding agent
-
visual-studio-harness
Agent Harness
-
Memory-Layered-Agent-Core
Persistent AI Memory System 2026 🧠 | Build Lifelong Assistant Agents
-
rune-forge-wizard
AI Development Harness for Claude Code 2026: Build CLAUDE.md & Agent Workflows
-
mudriknow
An AI assistant that sees your screen — not screenshots you paste. Alt+Space on any Windows app → instant answers, actions, or step-by-step guidance with an owl cursor. Open source, sandboxed, works with any LLM.
-
llm-wiki-patterns
🚀 LLM Wiki Graph Studio 2026 - Smart Research, Lint & Content Pipelines
-
mcp-remote
The bridge for remote MCP — seamless OAuth, resilient auth recovery, production-grade reliability
-
trytokka
TryTokka — AI API spend alerts (Scout). Synced spend across OpenAI, Anthropic, Gemini & more. By Acsaven.
-
aibti
Analyze your prompt history to determine your AI interaction style and behavioral patterns using local CLI tools.
-
claude-skills
Open-source Claude Code skills that bring planning, building, and verification gates to agentic coding workflows.
-
Codeably
Autonomous coding agent. Bring your own API key. 7 providers. Zero cost forever.
-
ctxone
Persistent, searchable, accountable memory for AI agents — the shared team memory layer. Eliminate context anxiety.
-
9router-v2
Self-hosted AI gateway — one endpoint, many providers, auto-fallback. OpenAI-compatible REST API with Cloudflare Workers AI automation.
-
apogee
Local-first terminal coding agent for any OpenAI-compatible endpoint — local or cloud. Full agentic tool loop, OS-enforced sandboxing (Landlock / seatbelt / Windows token), sessions, MCP, and A/B-measured mechanisms that make even small LLMs (4B–35B) deliver. Go + Bubble Tea.
-
vegaloom
One writes, one reviews — worker 与 reviewer 上下文隔离的 AI 编码工作流 Harness，以项目验证命令、风险门禁和运行证据判断任务能否完成。
-
scribe
AI-powered Git Commit Assistant that generates clean, meaningful commit messages from your staged changes using LLMs.
-
Obsidian-vault-api
Obsidian plugin that exposes your vault as a local MCP server for Claude Desktop app
-
grounded-reasoning
Zero-token, precision-guaranteed relation-algebra verifier for LLM/agent multi-hop reasoning
-
first-run
Embeddable customer-activation agent for small B2B SaaS companies
-
AlfredOS
An open-source, self-hostable, multi-user, multi-persona, security-hardened agentic OS.
-
DMJ-Dataset-Builder
Automate the preparation, validation, and merging of high-quality instruction-tuning datasets for Large Language Models.
-
Friday
Open-source JARVIS-class desktop AI. Voice personality, cron automations, screen/camera vision, 3D Holodeck, hand gestures, Google Calendar/Gmail, streaming chat — all local, no cloud.
-
AladdinAI
AladdinAI: open-source BYOI (Bring Your Own Infrastructure) AI Agent platform. Connect your own VMs, NVIDIA NIM, OpenAI, Anthropic, Ollama — build and manage AI agents visually.
-
readme2demo
Verified tutorials and demo videos from your README. An AI agent runs it in a hardened Docker sandbox and replays it in a fresh container before anything is published.
-
amarnai
Open-source, self-hostable AI email triage assistant for Gmail. Sorts your inbox into a custom taxonomy; drafts require approval, never auto-sends.
-
agentweb
Turn websites into fast CLI commands that any coding agent can use
-
ollama-mesh
The control plane for self-hosted AI inference. Warm-state GPU routing, multi-runtime orchestration across Ollama, vLLM, llama.cpp, and TGI. Single Go binary. Apache-2.0.
-
fak
fak — the Fused Agent Kernel: one Go binary for AI agent loops. Wrap Claude Code/Codex/Cursor, keep long sessions cache-efficient, route work per call, run local GGUF models, and adjudicate tool calls.
-
francois
Mission control for your Claude Code fleet — a native desktop app (Tauri 2 · Rust · React) to run and supervise multiple Claude Code sessions: live transcripts, diffs, subagents, MCP servers, and a real shell in one window.
-
ragleap-core
The open-source core of RagLeap — a self-hosted RAG chat engine (document ingestion, retrieval, citations) powering RagLeap's full AI business manager: Voice AI, WhatsApp/Telegram/Discord bots, database & CRM integrations, workflow automation, and a private executive assistant. Foundation layer — hosted platform at ragleap.com
-
oracle-forms-mcp
MCP server that exposes Oracle Forms modules (.fmb/.mmb/.pll/.olb) — blocks, triggers, PL/SQL, object XML — to AI assistants for legacy modernization and code review.
-
automaton
AI coding agent framework — portable, stage-gated harness for Claude Code, Codex, and OpenCode
-
hermes-agent-desktop
Automate desktop tasks and workflows using the Hermes agent for efficient local interaction.
-
chatbot-saas
RAG-powered chatbot-as-a-service — embed an AI chatbot trained on your own docs into any website
-
partyline
One wire, every agent — a shared telephone line for Claude Code agents. (It's a JSONL file.)
-
twin-brain
A second brain that builds itself: Claude Code maintains a persistent, interlinked Markdown wiki you own, with a local web app, Apple Calendar/Reminders integration, and token-budgeted automation. No database, no API keys.
-
sur9e
Self-hosted AI job-search toolkit: evaluates job offers, screens postings, tailors CVs, and tracks applications — all locally, inside Claude Code / Codex / OpenCode, with a web UI on top.
-
scribe-describe-generate
🚀 Sago AI: Generate Any App from a Markdown Description in Seconds (2026)
-
aurora
Open-source AI gateway — route LLM traffic across OpenAI, Anthropic, Gemini, Groq & 30+ providers via a single API. Self-hosted, no vendor lock-in.
-
no-more-fomo
Track AI news daily and get one concise, source-linked digest with summaries, context, and real links
-
icode-skill
A 6-step coding workflow for Claude Code — Plan → Review → Finalize → Code → Deep Check → Audit. Run all at once or step-by-step, switch models between steps. Claude Code 六步编码工作流：计划 → 审查 → 定稿 → 编码 → 复检 → 终审，一步到位或分步执行，步骤间可切换模型。
-
trimwire
Local gateway that prunes Claude Code's API context in-flight — dedup, purge failed calls, trim bloat, strip old screenshots. Anthropic-sanctioned (ANTHROPIC_BASE_URL), no CA cert, no restart.
-
3ngram
Persistent, typed memory for AI agents — open-source MCP server, REST API, SDK, CLI, worker, and self-host backend.
-
epicurus
Self-hosted, modular, local-first personal-assistant platform — an AI agent plus pluggable integration modules.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
VecMem
Manage LLM agent memory with a resource-aware dual-tier system that uses HNSW indexing to balance short-term context and long-term knowledge retention.
-
tech-brief
Daily tech-watch digest (AI, dev, DevOps, data, cloud). Auto-published from my watch on baptisteblouin.fr
-
agenticloop
Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work
-
jarvis-os
Jarvis OS - an autonomous AI personal assistant for productivity, executive function coaching, and multi-channel communication (Telegram, Slack, WhatsApp, Discord)
-
Dezin
A local-first, tasteful design generator. Describe what you want; your own coding-agent CLI (Claude Code, Codex, Gemini, Cursor) builds it as a real artifact, held to a strict anti-AI-slop standard. BYOK, nothing leaves your machine.
-
eco-mesh-sdk
Mica Plugin 2026: Route AI Inference Through Green Energy MVM Nodes to Cut Token Costs by 60%
-
ai-jury
Stdlib-only Python CLI that runs native coding-agent CLIs (Claude Code, Codex, Antigravity) + a free local model as one review jury — review a diff/PR/issue, debate, verify, synthesize one verdict (chair or panel vote). Local-first, secure by default.
-
awesome-ai-handbook
A practical guide to AI: from running your first local model to building your own agents. 52 files covering LLMs, Ollama, RAG, prompt engineering, machine learning, AI agents, and local AI tools.
-
MojoVec
Vector DB implementation in Mojo
-
bike4mind
The open-core AI workbench — notebooks, agents, RAG, voice, and images across any model: OpenAI, Anthropic, Google, xAI, or local via Ollama/vLLM. BSL 1.1, auto-converting to Apache-2.0 on a two-year clock. Your AI keeps running when theirs doesn't.
-
AI-native-engineer
Tracking my journey into AI engineering, one module at a time. Fundamentals to agents, with hands-on projects. Open to all.