THE ENGINEER BEHIND RECURSIVEINTELL
I build agent runtimes, persistent memory, and the infrastructure that connects execution to inspectable outcomes.
My current work spans Rust, Python, and TypeScript across Ares, Recursive Agent, semantic-memory, proveKV, and recovery-oriented workstation tooling. I’m interested in engineering roles where agent reliability, developer infrastructure, local-first systems, and explicit failure semantics matter.
CONTRIBUTIONS & RECOGNITION
Accepted upstream code and public recognition from the agent community. Follow the original sources.
ACCEPTED UPSTREAM CONTRIBUTION
My cluster-manager fix was accepted into NVIDIA’s Personal AI Router. Trust-change notifications now follow successfully persisted endorsement changes, with regression coverage for duplicates and failed writes.
An accepted open-source contribution to NVIDIA PAIR. This does not imply employment, sponsorship, or a commercial partnership with NVIDIA.
COMMUNITY RECOGNITION
Teknium, creator of Hermes Agent, highlighted my RecursiveIntell-enhanced Hermes demonstration and later reposted my work. That work has grown into Ares, my downstream agent workbench.
This is a public interaction around Josh’s engineering work, not a customer testimonial, partnership, or product endorsement.
A SHORT INSPECTION PATH
Start with the accepted NVIDIA PAIR fix, then explore Ares, memory, and the supporting systems. Each project makes its evidence and development status visible.
Duplicate endorsements and unsuccessful persistence must not announce a cluster trust change that did not happen.
Changed the cluster manager to announce successfully saved endorsement changes. Added regression coverage for duplicates, failed writes, re-pins, concurrent submissions, and persisted read-back.
NVIDIA Personal AI Router PR #62 was merged on September 23, 2026 as afdf9977c4c15029523aa4e1f965b2f8cc0e559c. The accepted patch and its review are publicly inspectable.
An accepted open-source contribution to NVIDIA PAIR. This does not imply employment, sponsorship, or a commercial partnership with NVIDIA.
A long-running agent needs a stable runtime, inspectable outcomes, and explicit control over its integrations.
An isolated Ares launcher and runtime control plane with immutable releases, atomic runtime selection, doctor/status checks, rollback, and opt-in RecursiveIntell integrations.
Source reviewed October 1, 2026 at Ares revision fadd47d7330445969cd99863e736c9b5dbfced54. The repository documents inherited Hermes surfaces, Ares-owned lifecycle code, gated execution, and external services separately. The September integration case remains available as a dated historical snapshot.
Ares is an independent RecursiveIntell downstream distribution, not an official Nous Research product. Source presence does not establish installed activation, every provider/platform combination, or production fitness.
Agent memory must persist, retrieve relevant prior state, preserve provenance and time, and remain operator-owned.
A Rust-first memory engine, MCP access layer, agent integration kits, and self-hosted Mnemes server with explicit ownership boundaries.
Public repositories, crates, documentation, tests, and a dedicated product/proof surface.
Public artifacts establish implementation scope, not customer adoption, universal correctness, or production fitness.
Agent plans and claims lose value when evidence identity, promotion rules, execution history, and failure states remain implicit.
Public Rust components for claim/evidence history, typed graph execution, receipt-bearing tool paths, and bounded orchestration.
Published crates, public source, schemas, examples, and test surfaces that can be inspected directly.
Receipts report observed execution. They do not prove factual truth, authorization, security, or task success.
A workstation supporting long-running AI work needs a recoverable operating environment without silently taking storage, credential, or device authority.
A Fedora 44 recovery-oriented workstation installer prototype packages bounded Wi-Fi recovery, targeted PCIe ASPM mitigation, TLP policy, disk reporting, health projection, and Hermes Workbench profiles while leaving destructive storage and identity choices interactive.
Public source includes a structurally checked hardware-target ISO candidate, a disposable BIOS/QEMU install-and-boot fixture, project tests, and a sanitized evidence receipt dated September 6, 2026.
The repository remains NO-GO for physical USB writing or laptop installation. UEFI installed-system behavior, physical-media validity, full workstation restoration, and hardware safety remain unverified.
KV-cache and hybrid-state work needs explicit identity, inspectable formats, and evidence that separates storage wins from model-quality costs.
A receipted two-tier content-addressed cache pool stores one shared cold prefix plus per-agent hot shells, with explicit codecs, manifests, and baseline contracts.
The current N=8 receipts report 40.50× versus an f32-raw baseline for the f32-radii profile and 76.54× for BlockLogU8-radii; the fp16-equivalent ratios are 20.25× and 38.27×.
The current cache-aligned continuation check also degrades from 7.203125 oracle PPL to 24.234375 (+236.44%). N=8 PPL neutrality, framework-cache reduction, decode speedup, and production fitness are explicitly not claimed.
Resource-constrained AI needs smaller representations without hiding formats, quality budgets, or exact fallback paths.
Experimental Rust quantization and compression primitives with explicit codecs, benchmark surfaces, and raw/exact escape hatches.
Published package records and public source for turbo-quant and related components.
No comparative performance or memory-savings claim is published here without a reproducible, revision-bound benchmark.
The semantic-memory fixture exercises supersession, historical reconstruction, replay, namespace isolation, and integrity rebuild. It demonstrates declared local scenarios; it does not establish factual truth, production fitness, or model-level prompt-injection resistance.
WORKING TOGETHER
I’m open to engineering conversations and focused consulting engagements. A useful first conversation names the system, the constraint, and what you need to change.
Explore consulting →