Havuz

A terminal-native AI agent runtime built in Rust. Interactive chat, parallel agent orchestration, and autonomous supervision.

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and

Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.

Capka AI — An open-source, self-hosted sandbox for AI agents. A community-driven alternative to Claude's Cowork

Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

🤖 Bots you run yourself: a daemon on your machine runs each bot through Pi, with web, iOS and macOS apps.

The DeepSeek and OpenRouter Harness built on Elixir

Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.

An agent that edits your Word and Excel files — then looks at them, through real Microsoft Office, to check its own work

AI 厂商动态别挨家追：每天巡检 OpenAI、Claude、Gemini、DeepSeek、通义、Kimi 等的官方博客与更新页，生成可订阅的 RSS，英文原文逐段精译为中文，并附 70 家免费额度 / 限时活动总表（实时抓自官方页、带官方链接可复核）

Distribute AI Skills as Composer dependencies

NOW you can let AI agents make code changes without losing engineering control.

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-

Whole-book translation pipeline — scouts the book, translates in context, edits, adds footnotes. epub, fb2, pdf, txt, html in; epub, fb2, ht

Source-linked collection of published AI model benchmark scores.

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks (NeurIPS 2026 Evaluations and Datasets Track)

AI travel planning engine with deterministic route scheduling, verified POIs, and fact-grounded LLM generation.

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Minimize AI and Agent failures into minimal reproducible traces.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

Run a 28.9M-parameter TinyLM on ESP32-S3 with an RP2040 OLED display node for fully local embedded AI inference.

Verified AI dependency migrations. Finds which of your lines a version bump actually breaks, fixes them, and proves the result still compile

Continuous red-team + latency-benchmark CI for LLM apps — promptfoo scans, deterministic security gate, p95 budgets. One DeepSeek key runs i

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

Run Claude Code and OpenCode on your Android phone, no computer needed. Or follow and steer agents on your computer: live sessions, tool app

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

Self-hosted mobile web chat UI for Claude Code — drive your real local claude CLI from your phone. Same CLAUDE.md, MCP, skills, login; any g

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a

A chatbot, with a large language model split across its users, entirely in the browser.

A team of AI agents that runs your job search — self-hosted, on your own LLM subscription. MIT.

Open Source Instruction Tuning LLM Training Library 2026

A desktop workspace (inspired by Grok Bot & Muse) for AI agents that collaborate, write code, and use tools. Run locally or on your own serv

B2B sales and marketing OS (aka GTM) inside Claude, GPT, Gemini, or Openclaw. Cold email to close. No dashboard. No SaaS.

Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit

An autonomous, always-on agent on your Android phone. It has its own browser, keeps a wiki memory of you, and hands the heavy jobs to your o

Tiny LLMs, Q4, in the browser. WebGPU lab inspired by yangqi0/petitgpt.

把公司 Agent 化:按你的组织架构给每个部门(业务/财务/人力/行政/运营/合规)嵌一个 AI agent,CEO 参谋长统筹全局经营,常驻飞书。 | Agentify your whole company: an AI agent per department, a chi

Local-first AI agent workbench for long-running projects: background work, built-in memory (no Docker), six web search services, MCP. macOS,

ONE API，LLM_Proxy，统一代理，支持请求响应自定义转换。

An operating workspace for Claude Cowork: decisions, context, next actions and routines in Markdown, so AI work stays grounded and team-owne

A cache-aware attention and forgetting layer for high-frequency everyday AI chat.

A web-reading tool for LLM agents that returns the parts of a page relevant to a question, verbatim

A free pit crew for your expensive coding agent: the superpowers development workflow, run by cheap workers.

OpenCode plugin for automatic API-key failover and rotation across multiple provider keys

ИИ для 1С-Битрикс: скиллы для Claude Code, Cursor и Codex, чтобы агент писал код по канону D7, а не legacy. 50 скиллов: ORM, контроллеры, ке

training your 0.1B llm from zero

Production-grade Agent Skills from Evil Martians — drop-in expertise for your AI coding agent