Personal AI, On Personal Devices
Python
fix: move focus areas and get-involved to top of roadmap, remove contributing from nav
Jon Saad-Falconb8bbbdbf55cc
diff --git a/docs/development/roadmap.md b/docs/development/roadmap.mdindex 5e91a65c..cb5cbb23 100644--- a/docs/development/roadmap.md+++ b/docs/development/roadmap.md@@ -1,30 +1,45 @@# Roadmap-OpenJarvis development is organized into **five independent workstreams**. Contributors can pick any track that matches their skills and interests — workstreams are designed to be worked on in parallel without blocking each other.+## Current Focus Areas-Within each workstream, items are organized by time horizon:+These are the areas where active development is happening and contributions are most impactful:-- **Near-term** — foundations and hardening of what exists-- **Mid-term** — significant new capabilities-- **Long-term** — frontier work requiring design exploration or research+- **Post-training data** — building datasets and training pipelines from execution traces to improve agent routing and tool selection+- **Multi-model orchestration pipelines** — coordinating multiple models within a single query (e.g., small model for classification, large model for generation)+- **Energy-aware routing** — using power consumption data from telemetry to optimize for energy efficiency alongside latency and quality+- **Plugin ecosystem** — community-contributed engines, tools, and agents distributed as Python packages+- **Federated memory** — memory backends that synchronize across devices++---++## How to Get Involved++1. Browse the workstreams below for items that interest you+2. Look for **Ready** items and **good first issue** tags+3. Find the matching [GitHub issue](https://github.com/open-jarvis/OpenJarvis/issues) and comment **"take"** to claim it — if no issue exists yet, [open one](https://github.com/open-jarvis/OpenJarvis/issues/new/choose) describing what you'd like to work on+4. Read the [Contributing Guide](https://github.com/open-jarvis/OpenJarvis/blob/main/CONTRIBUTING.md) for the full development setup, PR process, and code conventions++---++## Workstreams++OpenJarvis development is organized into **five independent workstreams**. Contributors can pick any track that matches their skills and interests — workstreams are designed to be worked on in parallel without blocking each other.Every item carries a maturity tag:| Tag | Meaning | Contributor guidance ||-----|---------|---------------------|-| **Ready** | Well-scoped, implementation path is clear | Pick it up — check issues for a spec or write one |-| **Design Needed** | Concept is clear but needs a spec before code | Start a design discussion or draft an RFC |+| **Ready** | Well-scoped, implementation path is clear | Pick it up — check [issues](https://github.com/open-jarvis/OpenJarvis/issues) for a spec or write one |+| **Design Needed** | Concept is clear but needs a spec before code | Start a [design discussion](https://github.com/open-jarvis/OpenJarvis/discussions) or draft an RFC || **Research-Stage** | Exploratory, needs investigation before designing | Read the relevant papers, prototype, share findings |-Items marked **good first issue** are especially suited for new contributors.-----## Workstream 1: Continuous Operators & Agents+### Workstream 1: Continuous Operators & AgentsOperators are OpenJarvis's key differentiator — persistent, scheduled, stateful agents that run autonomously on personal devices. The current tick-based architecture (OperatorManager → TaskScheduler → AgentExecutor → OperativeAgent) is solid but needs hardening for truly long-horizon autonomy.-### Where you can help+#### Where you can help| Item | Maturity | Details ||------|----------|---------|@@ -39,11 +54,11 @@ Operators are OpenJarvis's key differentiator — persistent, scheduled, statefu----## Workstream 2: Mobile & Messaging Clients+### Workstream 2: Mobile & Messaging ClientsPersonal AI must be accessible from the devices people actually carry. OpenJarvis runs on laptops, workstations, and servers — users interact via their phones. Channels bridge that gap. Today, WhatsApp (Baileys), Slack, and Telegram are bidirectional; iMessage is send-only; Android SMS does not exist.-### Where you can help+#### Where you can help| Item | Maturity | Details ||------|----------|---------|@@ -57,7 +72,7 @@ Personal AI must be accessible from the devices people actually carry. OpenJarvi----## Workstream 3: Secure Cloud Collaboration+### Workstream 3: Secure Cloud CollaborationPersonal AI's core tension: local models preserve privacy but lack capability; cloud models are powerful but require trusting a provider with your data. This workstream resolves that through **Minions-style collaborative inference** (local handles context, cloud handles reasoning) and **TEE-based confidential computing** (cloud cannot see your data even during inference).@@ -66,7 +81,7 @@ Personal AI's core tension: local models preserve privacy but lack capability; c- [Minions: Cost-Efficient Local-Cloud LLM Collaboration](https://github.com/HazyResearch/minions)- [TEE for Confidential AI Inference](https://openreview.net/forum?id=ey87M5iKcX) ([PDF](https://openreview.net/pdf?id=ey87M5iKcX))-### Where you can help+#### Where you can help| Item | Maturity | Details ||------|----------|---------|@@ -81,11 +96,11 @@ Personal AI's core tension: local models preserve privacy but lack capability; c----## Workstream 4: Tutorials & Documentation+### Workstream 4: Tutorials & DocumentationOpenJarvis has reference docs and four tutorials, but critical gaps remain in continuous agents, LM evaluation, learning approaches, and custom tools. Video tutorials are scoped as a contributor opportunity — written tutorials come first, with video scripts included so anyone can record.-### Where you can help+#### Where you can help| Item | Maturity | Details ||------|----------|---------|@@ -99,13 +114,13 @@ OpenJarvis has reference docs and four tutorials, but critical gaps remain in co----## Workstream 5: Hardware Breadth+### Workstream 5: Hardware BreadthPersonal AI means running on the hardware people actually own. Each new hardware target expands who can use OpenJarvis and generates data for the research agenda (energy, cost, latency tradeoffs across silicon).Adding a new hardware target involves up to four components: hardware detection in `core/config.py`, an inference engine adapter in `engine/`, an energy monitor in `telemetry/`, and an entry in the GPU specs database in `telemetry/gpu_monitor.py`.-### Where you can help+#### Where you can help| Item | Maturity | Details ||------|----------|---------|@@ -117,42 +132,3 @@ Adding a new hardware target involves up to four components: hardware detection| Intel Lunar Lake NPU via OpenVINO | **Design Needed** | 48 TOPS — most mature NPU software stack for x86 laptops. New engine wrapping OpenVINO GenAI. || Raspberry Pi 5 | **Design Needed** | CPU-only via llama.cpp ARM NEON for 1-3B models. $100 entry point for hobbyists. || Unified hardware benchmark suite | **Design Needed** | Standardized benchmark that runs the same workloads across all supported hardware, producing comparable energy/latency/throughput/cost numbers. |-------## Current Focus Areas--These are the areas where active development is happening and contributions are most impactful:--- **Post-training data** — building datasets and training pipelines from execution traces to improve agent routing and tool selection-- **Multi-model orchestration pipelines** — coordinating multiple models within a single query (e.g., small model for classification, large model for generation)-- **Energy-aware routing** — using power consumption data from telemetry to optimize for energy efficiency alongside latency and quality-- **Plugin ecosystem** — community-contributed engines, tools, and agents distributed as Python packages-- **Federated memory** — memory backends that synchronize across devices-------## How to Get Involved--1. Browse the workstreams above for items that interest you-2. Look for **Ready** items and **good first issue** tags-3. Read the [Contributing Guide](https://github.com/open-jarvis/OpenJarvis/blob/main/CONTRIBUTING.md) for the full process-4. Comment **"take"** on an issue to claim it-------<details>-<summary><strong>Version History</strong></summary>--| Version | Phase | Status | Delivers |-|---|---|---|---|-| **v0.1** | Phase 0 -- Scaffolding | :material-check-circle:{ .green } Complete | Project scaffolding, registry system (`RegistryBase[T]`), core types (`Message`, `ModelSpec`, `Conversation`, `ToolResult`), configuration loader with hardware detection, Click CLI skeleton |-| **v0.2** | Phase 1 -- Intelligence + Inference | :material-check-circle:{ .green } Complete | Intelligence primitive (model catalog, heuristic router), inference engines (Ollama, vLLM, llama.cpp), engine discovery and health probing, `jarvis ask` command working end-to-end |-| **v0.3** | Phase 2 -- Memory | :material-check-circle:{ .green } Complete | Memory backends (SQLite/FTS5, FAISS, ColBERTv2, BM25, Hybrid/RRF), document chunking and ingestion pipeline, context injection with source attribution, `jarvis memory` commands |-| **v0.4** | Phase 3 -- Agents + Tools + Server | :material-check-circle:{ .green } Complete | Agent system (SimpleAgent, OrchestratorAgent), tool system (Calculator, Think, Retrieval, LLM, FileRead), ToolExecutor dispatch engine, OpenAI-compatible API server (`jarvis serve`) |-| **v0.5** | Phase 4 -- Learning + Telemetry | :material-check-circle:{ .green } Complete | Learning system (HeuristicRouter policy, TraceDrivenPolicy, GRPO stub), reward functions, telemetry aggregation (per-model/engine stats, export), `--router` CLI flag, `jarvis telemetry` commands |-| **v1.0** | Phase 5 -- SDK + Production | :material-check-circle:{ .green } Complete | Python SDK (`Jarvis` class, `MemoryHandle`), multi-platform channel system (Telegram, Discord, Slack, WhatsApp, etc.), benchmarking framework (latency, throughput), Docker deployment (CPU + GPU), MkDocs documentation site |-| **v1.1** | Phase 6 -- Traces + Learning | :material-check-circle:{ .green } Complete | Trace system (`TraceStore`, `TraceCollector`, `TraceAnalyzer`), trace-driven learning, MCP integration layer |-| **v1.5** | Phase 10 -- Agent Restructuring | :material-check-circle:{ .green } Complete | BaseAgent helpers, ToolUsingAgent intermediate base, NativeReActAgent, NativeOpenHandsAgent, RLMAgent, OpenHandsAgent (SDK), `accepts_tools` introspection, backward-compat shims, CustomAgent removed |--</details>diff --git a/mkdocs.yml b/mkdocs.ymlindex 40c2dcb3..73869262 100644--- a/mkdocs.yml+++ b/mkdocs.yml@@ -164,6 +164,4 @@ nav:- Design Principles: architecture/design-principles.md- API Reference: api-reference/- Leaderboard: leaderboard.md- - Roadmap:- - Roadmap: development/roadmap.md- - Contributing Guide: development/contributing.md+ - Roadmap: development/roadmap.md