/uses

What I use

The version-pinned production stack as of 2026-05-03. Inspired by uses.tech. Every line cites a primary source where one exists. Updates daily.

9 categories18 primary sources citedRevalidates daily

Editor + agent loop

The two surfaces that touch every line of code I ship.

Cursor

Primary IDE.

Claude Code v2.1.117+

source

Agent loop with sandbox subprocess isolation enabled (CLAUDE_CODE_SUBPROCESS_ENV_SCRUB=1, PID-namespace isolation). verdict (the rubric I ship) is verified against this version.

tmux + neovim

Long-running sessions, paired with Cursor for review-on-cursor and ship-on-tmux.

Models in production rotation

Cascading router: simple → small models, complex reasoning → Opus / Sonnet / GPT-5.5 Pro. Gemini 3 Pro (preview) is eval-only.

Claude Opus 4.7

Strategy + planning + nuanced long-context. Internal id: claude-opus-4-7.

Claude Sonnet 4.7

Default workhorse for the Agentify orchestrator.

Claude Haiku 4.5

Routing + pre-classification. Internal id: claude-haiku-4-5.

GPT-5.5

source

OpenAI default. Internal id: gpt-5.5.

GPT-5.5 Pro

Hard-reasoning cases. Internal id: gpt-5.5-pro.

Gemini 3 Pro (preview)

source

Eval-only, not in production rotation. Used to triangulate when Anthropic + OpenAI disagree.

Mistral Medium 3.5

source

Active eval (GA 2026-05-01). Reasoning-toggleable; agent-runtime evals only, not yet in production routing fallback chain.

Runtime

Python 3.13

FastAPI, Pydantic v2, asyncio everywhere.

Node 22 LTS

Frontend + Edge runtimes.

Next.js 16.x

App Router, RSC, Edge + Node runtimes per route. Pinned ≥ 16.2.4 for CVE-2026-23869 + CVE-2026-29057.

TypeScript strict

All frontend + most scripts.

Rust

mnemo + critical infra paths, anywhere I need tight memory control + predictable latency.

Infrastructure

Vercel

Frontend + Edge functions for the portfolio + agent-airlock demo surfaces.

AWS Lambda + ECS

Long-running agent workloads at Attri.ai.

AWS Bedrock Managed Agents (Codex / GPT-5.5, limited preview)

source

Limited preview, Apr 28 2026. Wraps any Bedrock-Codex / GPT-5.5 invocation with the agent-airlock sandbox + capability-lease envelope. Optional bedrock_invocation_arn field shipped in /api/quote/schema.json v0.2.

E2B microVMs

Code execution sandbox for unverified agent-written code. Zero production incidents to date.

Azure WebPubSub

Real-time multi-tenant collaboration in Agentify.

PostgreSQL + pgvector

Primary store. Vector search lives next to the source of truth.

Agent identity (3-layer)

The non-human-identity stack as of mid-2026. See /writing/capability-lease for the manifesto + working wire format.

Okta for AI Agents (NHI binding, opt-in default-off, GA 2026-04-30)

source

Okta Universal Directory now hosts non-human identities (NHIs) for agents alongside humans. Lifecycle, audit, revocation are first-class. Opt-in module in the consulting starter from today; existing engagements get a one-line patch that binds capability leases to Okta NHI tokens.

W3C DID + Verifiable Credential

source

Cryptographic identity layer. /api/quote already accepts agent_identity.did + verifiable_credential per draft-2020-12 schema; verification on the v0.4 roadmap.

Capability-lease envelope (per-call authorization)

source

Time-bounded, scope-bounded lease per call with audit-emit channel. Anthropic Project Deal · Cloudflare Mesh · Cisco AWI converge on this shape.

Security tooling (open-source, mine)

I ship and dogfood the agent-security stack I write about. Cloud-agent repos are MIT-licensed; Provael (physical AI) is Apache-2.0.

agent-airlock

source

Runtime firewall: ghost-arg stripping, PII masking, RBAC, E2B sandboxing, cost circuit-breakers.

agent-audit-kit

source

SAST scanner for agentic systems: OWASP Agentic Top-10 + MCP Top-10 + 11-framework compliance reporting (SARIF).

verdict

source

7-dimension quality rubric for Claude Code; auto-hooks into the agent loop.

provael

source

Red-team & assurance for physical AI: attacks vision-language-action robot policies in simulation, reports an attack-success rate with a 95% CI + benign control. The action-layer counterpart to agent-audit-kit's text-layer scanning.

Observability

Datadog

Tracing + metrics across the multi-agent fleet.

Sentry

Error capture, frontend + backend.

PostHog

Product analytics + feature flags.

OpenTelemetry

Trace surface for agent steps.

Hardware

MacBook Pro M-series

Primary daily driver.

External 4K + ergonomic mech keyboard

12+ hour days demand it.

Physical AI (VAJRA hardware + Provael simulation)

Two tracks: VAJRA (build-in-public robot, see /vajra) on the hardware side, and Provael (VLA red-teaming, see /provael) on the simulation side.

Jetson Orin Nano Super (8 GB)

Edge compute. JetPack 6.3 (L4T r36.4.x).

Intel RealSense D435i

Depth + IMU sensing. Sourced, integration in progress.

Custom rover chassis

Differential-drive base, 5-DOF arm + parallel gripper. In fabrication.

ROS 2 Jazzy 0.13

source

Migrating from Humble; Nav2 stack on top.

NanoOWL @ 0.4.2

source

TensorRT-optimized OWL-ViT for open-vocabulary detection. Pinned commit-sha checked into the build manifest.

GR00T N1.7 (reference impl)

source

NVIDIA April 2026 release. Used as architectural reference, pinned to a specific commit-sha in the build manifest.

Cosmos 3 sim assets v3.1

Synthetic-data factory for affordance training.

LIBERO + robosuite + MuJoCo

source

Simulation suites Provael red-teams VLA policies inside. Deterministic, CPU-first for CI.

LeRobot (SmolVLA / π0)

source

Hugging Face VLA policies Provael targets. SmolVLA is the primary measured checkpoint.

uv + hatchling

source

Provael's Python 3.12 env + build toolchain: reproducible lockfile, fast CI.

Bumps land in lib/models.ts and on this page first. Feedback: sattyamjain96@gmail.com.