MAXIM
Roadmap
Development Status, Priorities, and Research Directions
Maxim is built in waves. Each wave stabilizes before the next begins, and every initiative has clear dependencies. This page tracks what's shipped, what's next, and where the project is heading long-term.
Contents
Current Status
Every active initiative and its current state at a glance. Status badges reflect the most recent milestone reached.
| Initiative | Status | Notes |
|---|---|---|
| Agent Mesh | Done | Complete (Phases Pre-7). Identity, protocol, transport, admission control, knowledge sharing, task delegation, distributed planning, SCN temporal coordination. mDNS + InferenceRouter deferred. |
| Generative Campaigns | Done | All stages shipped: narrative arcs, two-call narrator, planner integration, bridge-and-compress, ask_user tool, benchmark tiers, CLI simplification. 71 tests. |
| Embodiment Core | Done | All software phases shipped: SEM protocol, Cerebellum forward models, motor programs + engrams, composed failures, virtual entities. 164 tests. Hardware adapter deferred to future. |
| Simulation Benchmark | Done | All phases (0-6). Multi-model comparative testing, narrative transcriber, write-paper, Tier 3 hooks. maxim --sim benchmark --models X,Y --campaign Z |
| Python API | Done | Verb-based interface (run, imagine, connect, diagnose, observe, configure). Package: pymaxim. |
| Lane Tier Architecture | Done | FunctionRouter with tier routing (large/medium/small), fallback chains, auto-detection from hardware. Legacy lane names aliased. |
| Research Protocol | Done | Complete: mesh primitives, research tools, Writer + Reviewer, dual-LLM. maxim --sim research |
| Multi-LLM Scaling | Done | Complete. LeaderProxy, admission control, LaneMetrics, heartbeat, remote update. |
| Tool Refactoring | Done | All phases: say, think, examine, introspection tools, alias map, usage tracking, proactive tool list |
| Introspection API | Done | All phases. Observer (renamed from AUTIntrospector) + standalone run_campaign() shipped |
| Docker Sandbox | Done | Phase A (TmpdirSandbox + pain triggers) + Phase B (DockerSandbox + ContainerRunner + image catalog + unprivileged user) both shipped |
| Bio-System Wiring Hardening | Done | All phases shipped. Percept abstraction (SensoryModality, SensoryTag, SensoryGate), pipeline correctness, energy→NAc metabolic cost learning, decision_rationale provenance. Archived. |
| Mode System Refactor | Done | ~1,800 LOC removed. Strategies, exploration policy, and LiveModeIntent deleted. Sleep is now a tool. Skills module folded into Cerebellum. Dead runtime modules cleaned up. |
| DM MVP | Done | All 3 slices shipped: dm_schema.py, dm_runtime.py, tools_dm.py. 4 campaigns (heist, poisoned_crown, arena, darkened_cavern). ChooseTool + alias system, bio-system expectations checker. maxim --sim scenarios/campaigns/heist_v1.yaml |
What We Just Shipped
The most recent completions were DM MVP (bundled SEM characters, cascade DAG, ChooseTool, 4 campaigns) and Bio-System Wiring Hardening (percept abstraction, pipeline correctness, energy→NAc metabolic cost learning, decision_rationale provenance). With those done, all 14 major initiatives have shipped—the full cognitive stack is exercised end-to-end through narrative campaigns.
DM MVP
Bundled SEM characters with cascade DAG for narrative branching. ChooseTool + alias system for encounter choices. Bio-system expectations checker validates campaign results. 4 campaigns: heist, poisoned_crown, arena, darkened_cavern. maxim --sim scenarios/campaigns/heist_v1.yaml
Bio-System Wiring Hardening
Percept abstraction layer (SensoryModality, SensoryTag, SensoryGate), pipeline correctness fixes, energy→NAc metabolic cost learning, decision_rationale provenance field on Perception. 14/14 pipeline audit checks passing.
Mode System Refactor
~1,800 LOC removed. Strategies, exploration policy, and LiveModeIntent deleted. Sleep is now a tool. Skills module folded into Cerebellum motor programs. Dead runtime modules cleaned up (resilient.py, session.py, debug_status_server.py, monitor_registry.py).
Agent Mesh
Full mesh protocol through Phase Pre-7: AgentProfile identity, UMR naming, MeshMessage envelopes, LocalMessageBus, knowledge sharing between agents, task delegation, distributed planning, and SCN temporal coordination. mDNS + InferenceRouter deferred.
Generative Campaign Mode
LLM-driven narrative arcs (4 builtin + custom YAML), two-call narrator with AdaptivePlanner integration, bridge-and-compress for multi-arc continuation, ask_user tool, tiered benchmarks, --sim "goal" CLI simplification. 71 tests.
Lane Tier Architecture
FunctionRouter routes functions to capability tiers (large/medium/small) with fallback chains. Auto-detection from hardware VRAM. Legacy lane names (infer/review/record) aliased to tier names automatically.
Simulation Benchmark
Phases 0-6 complete: BenchmarkRunner, CLI (maxim --sim benchmark), 6 scenarios, narrative transcriber, write-paper pipeline, Tier 3 hooks for multi-model comparative testing.
Python API (pymaxim)
Verb-based interface: run, imagine, connect, diagnose, observe, configure. Lazy imports, structured return types. Published as pymaxim on PyPI.
Embodiment Core
SEM protocol (Sensor-Entity-Modulator), Cerebellum forward models, motor programs + engrams, composable failures, virtual entities. 164 tests. Hardware adapter deferred to future.
Multi-LLM Scaling
LeaderProxy with authentication + GPU metrics, admission control (concurrency caps + rate limiting), LaneMetrics per-tier counters, system heartbeat with stall detection, remote peer management (maxim peer update/restart/llm).
Research Protocol
Mesh primitives, research tools (record_experiment, query_experiments), Writer + Reviewer agents, dual-LLM orchestration. maxim --sim research
Next Up
All major initiatives are complete. These three priorities are independent and can ship in any order.
Hippocampus AUT Memory Refinement (~300-500 LOC)
Improve recall precision for campaign-specific queries. Modality-aware recall ("what did I hear?" vs "what did I see?") using SensoryTag metadata. decision_rationale search for why actions were chosen. Reduce observation capture spam.
DM Generative Architect (~500 LOC)
A --dm flag with goal strings generates campaigns via an architect persona. The architect interviews the user via ask_user tool, creates characters and encounters, and produces runnable campaign YAML. Builds on the shipped DM MVP.
PyPI Publication Ph3-6 (~200 LOC)
Multi-robot plugins via entry-point discovery (Ph3), CI/CD pipeline (Ph4), README rewrite (Ph5), Test PyPI dry run (Ph6). Package pymaxim phases 0-2 already shipped.
Research Directions
These are speculative, long-term directions. None are scheduled—they represent where the architecture could go once the current engineering work stabilizes.
ATL Self-Extension through Mechanism Discovery
Can Maxim's Anterior Temporal Lobe discover new concept categories and relationship types on its own? Today the taxonomy is hand-coded. A self-extending ATL would let the semantic memory grow in ways its designers didn't anticipate.
Federated Embodiments
Multiple Maxim instances sharing memory and causal models across different physical bodies. A robot that learns to open a door could transfer that knowledge to a different robot with different actuators—adapting the motor plan while keeping the causal structure.
Cross-Agent Affordance Delegation
When one agent discovers an affordance it can't act on (e.g., "this door has a handle but I have no gripper"), it could delegate to an agent that can. This requires a shared affordance vocabulary and a trust model for delegation.
Distributed Embodiment Construction
Multiple agents collaboratively assembling a physical structure, each contributing sensors and actuators. The Agent Mesh provides the communication substrate; this research explores what shared representations are needed for coordinated physical action.
Uncertainty-as-Pain
Mapping epistemic uncertainty to the PainDetector system. High uncertainty about a prediction would register as discomfort, motivating the agent to gather more information before acting—a bio-inspired approach to active learning and cautious exploration.
Dependency Graph
All major initiatives are complete. The three current priorities are independent of each other. Future work is demand-driven.
With all 14 major initiatives shipped, the three current priorities are independent and can proceed in any order. Hippocampus Refinement improves recall precision (the weakest link exposed by DM campaigns). DM Architect builds on the shipped DM MVP to generate campaigns from goal strings. PyPI Publication finishes getting the package into the ecosystem.
Future work (SEM Component DB, Hardware Adapter, Capability Agent, DM encounter library, Multi-AUT Party Mode) ships when demand surfaces—none are blocked, just not yet prioritized.
Contributing
Maxim is open source. Contributions are welcome—especially on items marked Not Started in the status table above.
Getting Started
- Clone the repo from github.com/dennys246/maxim
- Read
CLAUDE.mdin the project root—it covers architectural invariants, testing commands, and the module map - Run
maxim doctorto verify your environment - Run the test suite:
python -m pytest tests/ -x -q --ignore=tests/integration/test_memory_hub.py - Pick an initiative from the status table and open an issue or PR
Before You Start
The project has strong architectural invariants (one-way memory tiers, separate EpisodicMemory instances, LLM access only through the router). Read the CLAUDE.md section on invariants before making structural changes. The bio-system class names (Hippocampus, ATL, NAc, SCN, EC, AngularGyrus) are intentional and should not be renamed.