v0.6.8 · MIT
Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.
v1.0.0 · MIT
Hash-anchored read/edit/undo_last_edit tools for DeepSeek Harness (dsh). Every line gets a unique 3-char hash (A-Za-z0-9) that stays stable across edits; stale or ambiguous anchors are rejected, never fuzzy-matched. Undo persists across restarts.
v0.3.0 · Apache-2.0
Attestix - Attestation Infrastructure for AI Agents. DID-based agent identity, W3C Verifiable Credentials, EU AI Act compliance layer, delegation chains, and reputation scoring. 47 MCP tools across 9 modules.
v2.1.3 · MIT
Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
v1.2.1 · MIT
Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.
— · MIT
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
— · MIT
Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read
— · GPL-3.0
Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.
— · Apache-2.0
Local-first AI coding workflow for vibe coders, indie hackers, technical founders and product managers — catch missing tests and safety checks across Claude Code, Cursor, Windsurf, Replit, Lovable and Bolt.new.
v0.2.0 · no license
Fable 5.1 solution tracing. Prompting skills so Opus, Sonnet, Haiku, Grok, Gemini and open-weight models work like Fable 5.1
v0.3.0 · MIT
Make every model cheaper or better. Zero-config behavioral harness for Claude Code, with a reproducible 408-run benchmark
— · MIT
A bridge between Streamable HTTP and stdio MCP transports
— · MIT
Composable mathematics tools for agents
v6.3.0 · SEE LICENSE IN LICENSE
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 158 tools for Claude Code, Cursor, and Windsurf.
— · MIT
One-command installer for Sellable MCP in Claude Code, Codex, and Hermes
— · MIT
Sellable MCP server for Claude Code, Codex, and Hermes campaign workflows
— · no license
📟 Claude Code physical companion on M5Paper V1.1 e-ink. Multi-session dashboard, hardware approval (buttons + touch), AskUserQuestion option cards, CJK, USB/BLE, installable as a Claude Code plugin. / Claude Code 实体搭档,把 M5Paper 变成 Claude Code 的多会话看板 + 硬件审批面板。
v1.0.0 · no license
The shared task board for teams and their AI agents — connect over OAuth, every action signed.
v11.9.6 · MIT
Run multiple AI models against the same research, design, or coding task. Surface disagreements before you ship.
v1.1.1 · MIT
A Model Context Protocol server for Excel file manipulation
v1.8.6 · Apache-2.0
The missing open-source Kubernetes UI with a built-in MCP server for AI agents. See what's broken, why, and what changed. Issues, Topology, event timeline, Helm, GitOps, live service traffic, and cluster audits - all in one Go binary.
v1.4.3 · MIT
The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.
v0.8.5 · Apache-2.0
AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
— · MIT
PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.