Changelog

What shipped, when, and why.

Releases are tagged on github.com/s20sc/aeros-runtime. Every entry below points at a real commit or RFC.

v0.11.0 Partial · in flight

Hardware adapters & EmbodiedGovBench v2

First batch on main 2026-05-09 · full track tag pending real-hardware demo

v0.10.0 ships the governance core. v0.11.0 takes that core out in two directions: real-hardware adapters (Unitree G1 + Franka) and a public, multi-LLM benchmark with leaderboard.

  • Real Unitree G1 adapter — RealUnitreeG1Robot implements the Robot ABC against Unitree SDK 2 RPC. identity_hash byte-equal across g1_sim ↔ g1_real swap.
  • Real Franka adapter — RealFrankaRobot against the franka_ros2 driver, with workspace-bounds + speed-factor defense in depth.
  • Humanoid scenario suite — 4 G1 scenarios for NavigateECM + GraspAndPlaceECM, including an HR-4 enforcement check (operator-relax without signature must be refused).
  • Multi-LLM provider harness — matrix runner across Claude / GLM / Gemini / local-onnx. --cheap offline mode for CI.
  • Public leaderboard — docs/leaderboard/v0.11.0.json + docs/LEADERBOARD.md, regenerable, every row commit-pinned.
  • Paper experiment reproducibility — P11 / P12 / P14 claims now run as pytest tests/benchmarks/papers/; existing scripts kept as thin wrappers.
  • Operator docs — docs/BENCHMARK.md + docs/SCENARIOS.md covering full-matrix runs, env vars, cost estimates, scenario authoring.
  • Test baseline — ~2,347 passing on main.
What's deferred

The ROS 2 bridge process and the end-to-end real-hardware demo (G1 walks 1m + Franka grasps under live bridge) are deferred until a maintainer has both robots in physical reach. Those land as the v0.11.0 final tag along with the full hardware-track release notes.

View commits → Leaderboard →
v0.10.0 Released

Adaptive governance — identity, persona, memory, dreaming

Released 2026-05-09 · release notes

v0.9.0 shipped the governance bones: policy DSL, watchers, audit chain, recovery orchestrator. v0.10.0 makes governance adaptive — the robot can learn from its own episodic stream, evolve a persona, and reflect offline, all without flipping its identity hash.

  • Frozen Identity — IdentityManifest with seven hash inputs; identity_hash is byte-equal across upgrades, memory growth, and persona evolution. HR-1 regression on every PR.
  • Adaptive Persona — PersonaAdaptiveEvent typed vocabulary; asymmetric trust matrix (tighten = auto, relax = operator-signed Ed25519); 20/day cap with floor-clamp metric.
  • Layer 2 Semantic Memory — four fact kinds (skill_success_rate, object_property, zone_risk, interaction_pattern) with deterministic SQL aggregation, 100-event / 6h triggers, outbox-pattern emit durability, fail-closed timeouts.
  • Active Dreaming — offline reflection runner + DreamScheduler. Placeholder LLM guard refuses dream cycles when no real model is wired.
  • Unitree G1 Locomotion — ONNX bipedal locomotion policy with an AGPL-clean dependency stack; SimulatedUnitreeG1Robot.apply_twist walks pelvis ≥0.4 m / 1.5 s; live integration test wires NavigateECM to the real policy.
  • Test baseline — ~2,239 passing on main, 3 skipped, 0 failing (excluding known X11/EGL render flake).
Why this shape

The wedge: governance between LLM and actuator. v0.10.0 is what that means in code — identity is the substrate, persona is the policy, memory is the evidence, dreaming is the offline catch-up, humanoid is the proof-of-life. Five subsystems, one invariant: identity stays frozen through all of it.

View commits → Read the architecture
v0.9.0 Released

Governance bones — policy, watchers, audit, recovery

Released 2026-04 · first publicly tagged release

The governance core that makes everything else possible. Every capability call passes through admission, contract validation, policy check, watcher monitoring, recovery orchestration, and audit logging.

  • Runtime Core (Apache 2.0) — lifecycle, scheduling, execution loop, fault handler.
  • ECM Package System (Apache 2.0) — six-dimensional contract, v1/v2 dispatcher pattern, shadow executor.
  • Governance Layer — policy DSL, watcher system, four-level recovery (log / alert / intervene / halt), Ed25519 audit chain.
Release notes →

Earlier releases

  • v0.7.0 Pre-v0.9 architecture iterations
  • v0.6.0 ECM contract refinement
  • v0.5.0 Research baseline

See all tags on GitHub.

Want to see the numbers behind the claims?

Three measured guarantees: rollback success, replay determinism, planner action quality.

View benchmarks →