#ai-agents

Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.

MCP server for persistent AI memory — give any AI assistant long-term recall. Works with Claude, Kiro, Cursor, Windsurf.

A programmable voice platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream

mission control for agent skills

Contexer captures architecture decisions, constraints, conventions, and patterns from AI coding sessions. Replays them in next session so you don't have to explain it again. It works across multiple AI agents.

Your AI agent, safely operating your app in production, behind guardrails it can't cross. Deploy, scale, debug, and roll back real apps. Self-hosted, open source. Bring Claude Code, Cursor, or Codex.

Create conversational AI solutions with custom data and abilities using ChatBotKit for Go applications.

Rust toolkit for building LLM agent applications, e.g.: coding agents, assistant CLIs and multi-agent tools.

A self-improving reflection / skill-creation agent on LangGraph — the LangStage reference agent

A typed maintenance surface for the Claude Code harness — the Rust of agentic harnesses: declare a contract, gate on conformance.

Agent wallet, credential vault, and governance layer for autonomous AI agents

Set bounded, verifiable coding loops for Codex, Claude Code, Cursor, and SKILL.md-compatible agents.

Storage service for the Gas ecosystem. Provides a gas.StorageProvider implementation backed by AWS S3 (and S3-compatible services like MinIO, LocalStack, DigitalOcean Spaces).

Agent-first GitHub code exploration. GraphQL batching, code maps (~92% token reduction), AND search, repo discovery with README previews. Codemode TypeScript sandbox, MCP server. Go.

Define app scenarios, run them with any agent or automation tool, and preserve the evidence from every run.

Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

A streaming action runtime for AI agents, model serving, and multimodal APIs

Sandboxed TypeScript runtime for AI coding agents to query AWS — full SDK access with in-sandbox aggregation, credentials flow via IMDS and never enter the VM. Ships as a Claude Code plugin (MCP) and a standalone CLI, backed by Shuru microVMs or Docker.

An automation runtime AI agents can run, debug, and build for.

MGR — Método Governado por Rastreabilidade (Traceability-Governed Method): spec-driven development framework for coding agents, portable between Claude Code and GitHub Copilot

An open registry for discovering, verifying, and trusting AI agents.

For AI enthusiasts who try every new tool and watch their skills fragment. One source of truth for AI agent skills (SKILL.md) + cross-tool sync toolkit: MCP server, shared instructions, and one-command wiring for Claude Code, Codex, Gemini, Kimi, Cursor, Kilocode, OpenCode.

Pin feedback to the live UI. Hand it to Claude. An embeddable visual-feedback SDK — inspect an element, pin a comment, capture a screenshot; comments re-anchor across redeploys and reach Claude Code via MCP.

Self-hosted completion gate for coding agents: independent verification before done, durable evidence, CLI and local GUI.

Your agent test passed. Would it pass again? Checks whether AI agent test results are repeatable and varied enough to trust as a regression baseline. Reads Promptfoo and DeepEval runs you already have.

A deterministic code knowledge graph for coding agents — one static Go binary indexes code, routes, dependencies, k8s & docs; your agent answers from the store. No LLM, no DB, no MCP.

Local-first context gateway that helps AI coding agents read less, spend less, and stay grounded in your repo.

AI vision GUI automation for browsers, mobile apps, desktops, and games — no DOM, no selectors. Standalone or on top of Playwright / Selenium / Appium / pytest.

Опис репозиторію не опубліковано.

A type-safe-by-design, cost-limited virtual machine that enables the safe execution of untrusted code anywhere