awesome-ChatGPT-repositories
Section: CLIs · Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋
Entry
Appears in 6 awesome lists
Workflow engine for AI where agent work is captured as reviewable .nika.yaml DAG files, statically checked before execution (schema, permits, cost floor) with tamper-evident traces after. Local-first (Ollama, llama.cpp, vLLM), MCP client and server. AGPL-3.0 licensed.
Section: CLIs · Intent as Code | the workflow language for AI. One file, 4 verbs, one Rust binary. Local-first, any model, AGPL-3.0. 🦋
Section: Workflow · Intent-as-code workflow engine for AI data pipelines: reviewable YAML DAGs statically checked (schema, permits, cost floor) before execution, with tamper-evident run traces.
Section: MCP Servers · Read-only oracle for Nika AI workflows: validate .nika.yaml DAGs, explain findings, browse schema/examples, honest cost estimate — before a single token is spent (single Rust binary, config: command nika, args [mcp]).
Section: 4. Agentic AI & Multi-Agent Systems · Workflow engine for AI where agent work is captured as reviewable .nika.yaml DAG files, statically checked before execution (schema, permits, cost floor) with tamper-evident traces after. Local-first (Ollama, llama.cpp, vLLM), MCP client and server. AGPL-3.0 licensed.
Section: Applications · Intent-as-code workflow engine for AI: reviewable YAML DAGs statically checked (schema, permits, honest cost floor) before any token is spent. Single binary.
Section: AI & LLM Testing · Workflow engine for AI with testing built in: nika test pins a workflow's offline behavior as a golden snapshot (deterministic mock provider, zero keys) and replays it in CI; every run also leaves a hash-chained trace for post-hoc verification.
Python module for building complex pipelines of batch jobs. Handles dependency resolution, workflow management, visualization, and Hadoop integration. Built at Spotify and battle-tested in production. Apache 2.0 licensed.
"Use airflow to author workflows as directed acyclic graphs (DAGs) of tasks. The airflow scheduler executes your tasks on an array of workers while following the specified dependencies. Rich command line utilities make performing complex surgeries on DAGs a snap. The rich user interface makes it…
Cloud-native orchestration platform for developing and maintaining data assets including ML models. Declarative programming model with integrated lineage and observability. Apache 2.0 licensed.
Multi-cluster Kubernetes MCP server bridging Gemini CLI to kubeconfig and Kubernetes APIs. Manage clusters, policies, and 20+ CNCF project integrations across edge and cloud. Install via brew tap kubestellar/tap && brew install kc-agent.
Indexes coding-agent sessions already written to disk and serves them back over MCP with no LLM calls, embeddings, or API keys. The zero-dependency binary solves the memory cold-start problem for cross-session persistence and demonstrates that agent memory can be built on existing filesystem…
Source-available (FSL-1.1-ALv2) QA agent for natural-language web and mobile tests. Run agent-qa mcp for authoring, execution, artifacts, and failure triage; dashboard-backed tools need a running dashboard and dashboardUrl. Model and infrastructure costs are separate.
🟢 — Local CLI and MCP toolkit for agent-assisted reverse engineering of native binaries, JavaScript/Electron and .NET applications, Android artifacts, firmware, and browser/process behavior, integrating analysis providers including Hopper, Ghidra, and IDA. — note: provider and host requirements…;…
Native macOS control panel for the Android Emulator (dark mode, font scale, locale, TalkBack, network throttling, GPS mock, Layout Inspector in dp) with a built-in stdio MCP server (18 tools) that lets Claude Code, Codex, Cursor, and VS Code see and drive the emulator. Gives mobile coding agents a…