Code & AI agent sandboxes: read the guide

PandaStack

Open coreSandbox

The cloud for AI agents.

Homepage Docs Pricing Repository

Scanned 15 Oct 2026 · Schema v5 · features v21

From: $20/mo
Usage-based with monthly credit; paid base converts 1:1 to credit.
Free tier: Yes
No card required.
Isolation: Firecracker microVM
shares only the hypervisor
Regions: —
Privacy policy and repository describe multiple regions but no verified selectable hosted region names or locations were found. Self-host Terraform examples are not a hosted region catalog.
Capabilities: 31 / 61
5 partial · 25 fail · 0 not assessed
Agent readiness: 9/11 · 10/11
read · drive, pre-login surface

Advertised for

Untrusted code · Agent sandboxes · Code interpreter · Browser automation · Git hosted apps · Managed postgres · Serverless functions · Cron

Built for

Developers, then technical

· CLI/Python/TypeScript code hero; Firecracker, snapshot and vCPU terminology; deep API and self-host docs.

01 Pricing Usage-based with monthly credit; paid base converts 1:1 to credit.

Tier	EntryFree	Pro	Team	TopEnterprise
Price	$0/month; $5.40 usage credit, paused when exhausted	$20/month + usage above credit	$99/month + usage above credit	Custom annual contract
Includes	$5.40 monthly usage credit. 5 concurrent; 4GiB/sandbox; 2 sustained cores; 60 creates/hour; 1h lifetime, apps/DB exempt.	$20.00 monthly usage credit. 50 concurrent; 16GiB/sandbox; 600 creates/hour; 7-day idle TTL; 10 volumes each up to 10GiB.	$99.00 monthly usage credit. 500 concurrent; 64GiB/sandbox; 6000 creates/hour; 30-day idle TTL; unlimited seats; 50 volumes each up to 50GiB.	BYO-VPC / dedicated tenancy, custom quotas, SAML/SCIM/OIDC, audit streaming and advertised 99.95% SLA.
Seats	1	5	—	—
Storage	1 GB	100 GB	2500 GB	—
Transfer overage	$0/GB	$0/GB	$0/GB	—
Storage overage	$0.15/GB	$0.15/GB	$0.15/GB	—
vCPU hours overage	$0.054/h	$0.054/h	$0.054/h	—
Memory gb hours overage	$0.0162/h	$0.0162/h	$0.0162/h	—

Active vCPU-seconds, resident working-set GiB-seconds, provisioned GiB-month storage beyond quota.·Card required: No·pandastack.ai

02 Website design Desktop public website · assessed 15 Oct 2026

Complete assessment.

Desktop public landing, pricing and documentation entrance share pale backgrounds, dark oversized headings, generous whitespace, rounded panels and purple accents. Landing and docs add faint technical grids and gradient-highlighted headline words; pricing uses a centered introduction and four aligned plan cards. Coverage is limited to these public entry viewports, not authenticated product UI or documentation article layouts.

Corporate
Technical illustration

Landing page: captured
Pricing: captured
Docs: captured

03 Runtime Each fact carries its source; dots show confidence. Open a row for the evidence.

Isolation & lifecycle

Isolation primitive

Firecracker microVMshares only the hypervisor

Persistence

Ephemeral sandbox rootfs; durable named ext4 volumes and managed PostgreSQL; hibernation retains VM state.

Snapshots / forks

Snapshot/restore, disk-only fork(), live-state fork_tree, pause/resume and hibernate/wake.

Resources & limits

Storage

Host-local named ext4 volumes, snapshots and managed PostgreSQL 16. Free 1GiB, Pro 100GiB, Team 2500GiB included volume quotas.

Limits & quotas

Free: 5 concurrent sandboxes, 4GiB per sandbox, 60 creates/hour, 1-hour sandbox lifetime, 1GiB volume quota. Pro: 50 concurrent, 16GiB per sandbox, 600 creates/hour, 7-day idle TTL, 100GiB total volume quota (10 × 10GiB). Team: 500 concurrent, 64GiB per sandbox, 6000 creates/hour, 30-day idle TTL, 2500GiB total volume quota (50 × 50GiB). Enterprise: custom quotas. Complete machine-readable catalog retained in artifacts/live-pricing.json.

GPU

No GPU-backed offering found in public templates, pricing or API docs.

Access

Deploy interface

apisdkcligit-pushdockerfile

SDK languages

PythonTypeScriptJavaScript

Network & secrets

Egress controls

Hosted per-sandbox egress otherwise open; self-host operator can configure blocked TCP ports via PANDASTACK_BLOCKED_EGRESS_PORTS.

Secrets

App environment secrets encrypted AES-256-GCM, masked in API reads and logs, injected at build/run time.

Bring your own cloud

Enterprise BYO-VPC / dedicated single-tenant; self-host core independently available.

Placement & use

Jurisdiction

Terms governed by Delaware, USA; infrastructure may process data internationally, including the United States. No concrete region catalog found.

Advertised workloads

Untrusted codeAgent sandboxesCode interpreterBrowser automationGit hosted appsManaged postgresServerless functionsCron

04 Capabilities 31 pass · 5 partial · 25 fail · 61 of 61 assessed

Supported — Documented on the public surface and verified.
Partially supported — Exists with caveats: gated, thin, or enterprise-only.
Not supported — Checked and not offered.
Not assessed — Scanned before this capability was tracked. Not a lack.

Compute & storage 5/11

Persistent diskStorage that survives restart/stop (not ephemeral-only).

Supported

Object storageManaged S3-compatible / blob object store the platform PROVIDES to a user's workloads (buckets, presigned URLs). DISTINCT from persistent-disk (block/volume attached to an instance) and from a self-host dependency (source.self_host.deps[]=["object-storage"] is an infra dep to RUN an OSS tool — the opposite direction). SCOPE varies and matters: native first-class (Railway Buckets, Cloudflare R2) vs a sibling SKU / extension (Fly Tigris, Bunny Storage, DigitalOcean Spaces) — record which in the evidence quote / note. Admitted v15.

Not supported

Snapshots / forkingSnapshot or copy-on-write fork of a running instance (filesystem-only counts). Whether the snapshot also restores memory + running processes is recorded separately by memory-snapshot (v19).

Supported

Live-state (memory) snapshotsA snapshot / checkpoint / pause captures a running instance's MEMORY and PROCESS state and restores it, so running processes continue where they left off instead of a freshly booted instance with the same files. Counts whether user-triggered (snapshot, checkpoint, pause-to-storage) or used to restore pre-initialised state (memory snapshots for fast cold starts). Distinct from snapshots-forks (any snapshot or fork, including filesystem-only; a product passing that key may still fail this one) and from scale-to-zero (an idle-cost property; suspension may or may not keep memory). Actor multiplexing (see scale-to-zero) records its live-state half here — only when the suspended actor's MEMORY/process state is what comes back, not a freshly booted worker with the actor's files.

Supported

Scale to zeroIdle instances suspend at no / negligible cost. ACTOR MULTIPLEXING (many suspended stateful actors sharing a small pool of pre-warmed workers, woken on request — Agent Substrate, AX, kagent; Rivet's hibernating actors) has NO key of its own (proposal REJECTED v20) — score the idle-cost half HERE and the live-state half under memory-snapshot; the oversubscription ratio / density is a performance characteristic the registry does not key.

Supported

GPU computeGPU-backed instances available.

Not supported

Multi-regionCompute placeable in more than one geographic region.

Partially supported

Sandbox templates / custom imagesBuild reusable sandbox/VM images from an OCI image or Dockerfile (a base you fork instances from).

Supported

Cloud-init / ignition configCustomise a VM / microVM / instance at boot via cloud-init (or ignition) user-data — the same boot-metadata interface as AWS/Azure/GCP. Inject packages, users, SSH keys, files, and run-commands declaratively at launch. Distinct from sandbox-templates (a PREBUILT image you fork instances from) — this is PER-LAUNCH declarative customisation, not a baked image.

Not supported

Desktop / computer-use sandboxA virtual desktop (GUI) for LLM computer-use — browser + desktop automation, often via noVNC/VNC.

Not supported

Selectable isolation runtimeThe user chooses the isolation runtime per workload / environment / sandbox from more than one option (e.g. microVM vs gVisor vs plain container, native namespaces vs gVisor, gVisor vs VM). Records the CHOICE; the isolation_primitive facet still records the best-evidenced primary. A platform that switches runtime automatically without a user choice (e.g. gVisor forced for GPU) does not pass on that alone.

Not supported

Networking & delivery 4/9

Automatic HTTPSTLS endpoints provisioned automatically per workload.

Supported

Built-in reverse proxyPlatform routes external traffic to workload services.

Supported

Custom domainsBring-your-own domain via CNAME/DNS.

Supported

Public preview URLsShareable per-deploy / per-branch URLs.

Supported

Direct public IPv6Per-instance stable public IPv6 for raw TCP/UDP (beyond a managed HTTPS proxy) — e.g. mosh / raw sockets.

Not supported

Egress controlsConfigurable OUTBOUND network policy — egress firewall / allowlist / egress proxy on traffic LEAVING a workload. Scoped to OUTBOUND only (v15): private-network REACHABILITY between a user's own services is private-networking, not this. Static-egress-IP belongs here (an outbound concept).

Partially supported

Private networkingA platform-internal private network between a user's OWN services — service-to-service connectivity, VPC, service mesh, and/or service discovery, not exposed to the public internet. DISTINCT from egress-controls (OUTBOUND firewall/allowlist), reverse-proxy (PUBLIC inbound ingress), and direct-ipv6 (per-instance PUBLIC addressing). Admitted v15.

Not supported

Email send / receiveSend and/or receive email from the workload.

Not supported

Edge KV storeA globally-replicated key-value store read from WITHIN an edge runtime at the PoP (low-latency, eventually-consistent) — Cloudflare Workers KV, Deno KV, Fastly KV Store, Akamai EdgeKV, Vercel Edge Config. Distinct from first-party-db (a managed DATABASE service you provision and connect to) and from http-query-api (HTTP access to an external store) — edge-kv is colocated with the edge compute and read at the edge.

Not supported

Developer access 8/10

Public APIDocumented programmatic API.

Supported

OpenAPI specMachine-readable OpenAPI / Swagger spec published.

Supported

CLIOfficial command-line tool.

Supported

SDKOfficial client library/libraries.

Supported

SSH accessDirect SSH into workloads.

Supported

Filesystem APIRemote file operations over the API (list/read/write/watch/copy/upload) without SSH.

Supported

Git deployDeploy from a Git repo / push-to-deploy.

Supported

Private container registryHosted private image registry.

Partially supported

E2B-compatible APIDrop-in compatibility with the E2B sandbox API/SDKs — existing E2B client code runs against this product by changing the endpoint/domain + key, with no business-code changes. E2B itself passes as the reference implementation. Distinct from public-api / sdk (the product has its own API — this key says it also speaks another vendor's) and from self-host-oss (a self-hosted E2B-compatible server is scored on both).

Not supported

HTTP data APIQuery / read / write the stored DATA over plain HTTP/REST (or GraphQL) WITHOUT the native protocol driver (Postgres wire / Redis RESP) — agent- and edge-friendly data access via fetch(). The DATA plane; distinct from public-api (a control-plane / management API). Auto-generated-from-schema REST/GraphQL (PostgREST, pg_graphql) is a flavour of this.

Supported

AI & agents 4/12

Built-in coding agentShips a first-party AI coding agent in the product.

Not supported

Agent skillsInstallable / declarable agent skills or tools.

Not supported

AI app builderPrompt-to-app / vibe-coding generation surface.

Not supported

MCP serverExposes a Model Context Protocol server for agents.

Supported

MCP clientActs as an MCP client / consumes MCP tools.

Not supported

MCP-server hostingRun/host MCP servers as a workload on the platform (distinct from exposing a first-party MCP control server — that is mcp-server).

Supported

LLM gatewayRoutes LLM API calls through the platform (multi-provider).

Not supported

BYOK for LLMsBring-your-own LLM provider keys.

Supported

Model inference API (first-party)A FIRST-PARTY hosted LLM/model inference API — the provider serves its OWN catalogue of (usually open-weight) models behind a (typically OpenAI-compatible) endpoint, billed per token. Distinct from llm-gateway (a multi-PROVIDER proxy/router for YOUR calls to external providers like OpenAI/Anthropic) and from byok-llm (bring your own provider keys) — here the platform IS the inference provider, serving its own models.

Not supported

Autonomous QA agentA first-party AUTONOMOUS AI agent that QA-TESTS a running app / implementation — exercising it like a real user (clicking through flows, checking behaviour) and reporting bugs/defects (often back to a coding agent, or before a human review). Distinct from built-in-agent (a code-AUTHORING agent — this one VERIFIES the result, it does not write the feature; a product can ship both), from ai-guided-code-review (organises a diff for a HUMAN to review — not an autonomous tester), and from observability (runtime metrics/logs, not active testing).

Not supported

Credential-injection proxyThe platform holds real secrets OUTSIDE the workload and injects them on the wire (an egress / broker proxy swaps a placeholder or phantom token for the real credential on matching outbound requests), so code running in the sandbox — e.g. an untrusted agent — never sees or can exfiltrate the real key. Distinct from secrets-management (storage + injection INTO the workload as env vars/files — the workload holds the secret) and from egress-controls (outbound allow/deny POLICY; a product can have an allowlist without injecting credentials, and vice versa).

Not supported

Preinstalled coding agentThe platform installs and launches a THIRD-PARTY coding agent (a harnesses.yml entry — Claude Code, Codex, OpenCode, Pi ...) inside a workspace/sandbox it provisions, with the agent's auth wired in (your own account or API key), so you start an agent session rather than an empty box. Distinct from built-in-agent (a FIRST-PARTY agent the vendor ships) and from harnesses[] (which records that a harness CAN target the product, not that the product runs it for you).

Supported

Data 3/4

First-party databasePlatform-provided managed database.

Supported

Database branchingCopy-on-write branch of a DATABASE (schema + data) as a dev-lifecycle primitive — branch your data like code, usually instant via a metadata operation. Distinct from snapshots-forks (forks a running compute INSTANCE / VM state) and from preview-environments (a full per-PR environment that may USE a DB branch). For a data product a CoW branch maps HERE, not to snapshots-forks.

Supported

Vector searchFirst-class storage, indexing, and similarity search of vector embeddings — a native vector type/index or a managed vector DB. The data-layer primitive for RAG / semantic retrieval.

Supported

Ephemeral instant DB (no-signup)Provision a working, usable instance via a single command / HTTP call with NO account, signup, or card — typically time-boxed (expires unless claimed). A zero-onboarding path an agent can hit directly.

Not supported

Platform & operations 3/6

Scheduled tasksCron / scheduled job primitive.

Supported

Durable workflowsDurable execution / long-running workflow primitive.

Not supported

Preview environmentsA full EPHEMERAL environment spun up per PR / branch — compute + addons + (often) a DB branch — torn down on merge. More than preview-urls (which is just a shareable URL for one deploy).

Supported

Built-in observabilityFirst-party metrics / logs / tracing / APM / profiling included in the platform (no third-party stack required to see what a workload is doing).

Supported

Managed CI/CD runnersPlatform-hosted, drop-in CI/CD runner VMs (GitHub Actions / GitLab), typically faster and cheaper than the CI vendor's own hosted runners, billed per runner-minute; isolated + ephemeral per job. Distinct from git-deploy (push-to-deploy of an APP) and scheduled-tasks (cron) — this is managed CI COMPUTE you point your existing pipelines at.

Not supported

Project template marketplaceA marketplace / gallery of prebuilt PROJECT STARTER templates (apps or websites) a user clones or launches a new project from and then customises — the "start from a template" surface of a builder / PaaS. Distinct from sandbox-templates (a COMPUTE base IMAGE you fork runtime INSTANCES from — Dockerfile / OCI), from app-builder (the prompt-to-app GENERATION surface — a product can have both), and from one-click OSS-app catalogues / helm-addon-marketplace (deploy a FINISHED app as-is, not a starter you build on).

Not supported

Organisation & security 4/9

Built-in authPlatform-provided authentication / IAM for workloads.

Not supported

SSO / SAMLEnterprise single sign-on.

Partially supported

Secrets managementFirst-class secrets storage / injection.

Supported

TeamsMulti-user team accounts.

Supported

SharingShare a running workload/resource via link (optionally gated).

Supported

BYOCRuns inside the customer's own cloud account.

Partially supported

Deploy into customers' VPCsA SaaS vendor uses the platform to deploy and operate ITS software inside ITS CUSTOMERS' cloud accounts / VPCs (nested or "customer BYOC"), managed from the vendor's control plane. Distinct from byoc (your own workloads in your own cloud account).

Not supported

Workload identityThe platform gives each workload its own verifiable identity (OIDC token, SPIFFE SVID, cloud IAM federation) that it exchanges for short-lived credentials, so no long-lived static secret is stored or injected. Distinct from secrets-management (stores / injects static secrets) and credential-injection-proxy (swaps real secrets in on the wire).

Not supported

Self-host / OSS coreOpen-source core that can be self-hosted.

Supported

05 Agent readiness Pre-login surface · counts, not a grade

Can an agent read it?

parse-ability · docs, metadata, machine-readable surfaces

9/11

7 full · 2 partial · 82% of applicable checks

llms.txt
Supported
“https://www.pandastack.ai/llms.txt — substantive product description, docs, pricing and self-host links.”
llms-full.txt
Not supported
“https://www.pandastack.ai/llms-full.txt and docs-host variants returned 404 HTML, not a comprehensive text corpus.”
robots.txt AI policy
Partially supported
“https://www.pandastack.ai/robots.txt — User-Agent: *; Allow: /; no named AI user-agent policy.”
JSON-LD
Supported
“https://www.pandastack.ai/ — Organization, WebSite and SoftwareApplication with description and offers.”
Sitemap
Supported
“https://www.pandastack.ai/sitemap.xml — HTTP 200 substantive XML URL catalog, 172,342 bytes.”
Meta tags
Supported
“https://www.pandastack.ai/ — descriptive title, description and Open Graph metadata.”
Markdown negotiation
Not supported
“Homepage and docs with Accept: text/markdown return HTML; quickstart.md returns 404.”
Content efficiency
Supported
“Homepage readable text / HTML bytes measured 0.0528 (>5%); retained landing.html and text extraction.”
Docs discoverable
Supported
“https://www.pandastack.ai/ — first-class docs navigation to https://docs.pandastack.ai/.”
Machine-readable pricing
Supported
“https://www.pandastack.ai/pricing/ — structured tier cards and public GET https://api.pandastack.ai/v1/pricing JSON.”
No anti-bot wall
Partially supported
“One Accept:text/markdown probe returned HTTP 403 browser_signature_banned; same URL succeeded with browser-like User-Agent and foxcrawl. Other public sources fetched. Intermittent public-path block, not persistent scan limitation.”

Can an agent drive it?

act-ability · APIs, SDKs, MCP, credentials, webhooks

10/11

9 full · 1 partial · 91% of applicable checks

Public API
Supported
“https://docs.pandastack.ai/docs/reference/rest-api/ — bearer-auth endpoint and operation reference.”
OpenAPI spec
Supported
“https://api.pandastack.ai/openapi.json — HTTP 200 valid OpenAPI 3.1.0 JSON, 116 paths.”
MCP server
Supported
“https://docs.pandastack.ai/docs/agents/mcp-server/ — documented hosted endpoint https://api.pandastack.ai/mcp plus per-sandbox JSON-RPC.”
SDK packages
Supported
“https://docs.pandastack.ai/docs/sdk/python/ and sdk/typescript/ — official pandastack and @pandastack/sdk; advertised APIs not executed.”
Auth documented
Supported
“https://docs.pandastack.ai/docs/reference/rest-api/ — JWT-only token endpoints and bearer-key workload endpoints documented.”
Self-serve credentials
Partially supported
“https://docs.pandastack.ai/docs/reference/rest-api/ — POST /v1/me/tokens requires existing JWT; initial sign-in remains human, no verified unauthenticated programmatic signup.”
Webhooks
Supported
“https://docs.pandastack.ai/docs/sandboxes/webhooks/ — endpoint registration, event types, retries and HMAC-SHA256 signature verification.”
CLI tool
Supported
“https://docs.pandastack.ai/docs/sdk/cli/ — official pandastack CLI documented; stale local build path separately flagged.”
Error model
Supported
“https://docs.pandastack.ai/docs/reference/errors/ — JSON error string, HTTP code table and contextual quota fields.”
Rate limits documented
Supported
“https://docs.pandastack.ai/docs/reference/errors/ — 50 burst / 25 per second per workspace, Retry-After: 1; hourly create limits in live tier JSON.”
Agent config files
Not supported
“GET /agents.md and /.well-known/agent returned 404. No installable agent configuration/skills listing found in reviewed llms/docs/repo sources.”

06 Coding harnesses Which agents and IDEs are documented to run here

Advertised integrations 7

Claude Code Anthropic
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
Codex CLI OpenAI
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
OpenCode opencode
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
Amp Sourcegraph
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
Gemini CLI Google
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
GitHub Copilot GitHub
Supported
“Every terminal coding agent with a public CLI, in one image: claude , codex , opencode , amp , grok , gemini , copilot .”
Source docs.pandastack.ai
Advertised agent-template installation and BYOK, not executed verification.
Cursor Anysphere
Supported
“Claude Desktop, Cursor, mcp-cli, and other MCP clients”
Source docs.pandastack.ai
MCP client integration, not preinstalled IDE.

Plausible compatibility 10

Derived, not stored: the product passes SSH access, so any CLI coding agent is installable inside it. This is plausible compatibility, not a supported integration.

Aider
Antigravity
Devin
Droid
Goose
Hermes Agent
Kilo Code
Kiro CLI
Pi
Qwen Code

07 Compliance & regions Standards held, with ordinal rigor; never a score

Certifications held 3

PCI DSS
self-attestedhosted
“we self-assess annually under SAQ A”
Source pandastack.aiConfidence: medium
CCPA
self-attestedhosted
“We do not sell personal information”
Source pandastack.aiConfidence: medium
GDPR
self-attestedhosted
“We act as a processor for Customer Content”
Source pandastack.aiConfidence: medium

Regions —

Regions are not disclosed on the public surface.

Privacy policy and repository describe multiple regions but no verified selectable hosted region names or locations were found. Self-host Terraform examples are not a hosted region catalog.

Legal

Privacy notice Terms of service

08 Open source Apache-2.0 · fetched by machine, not quoted from marketing

Licence & repository

Licence: Apache-2.0OSI
Primary language: Go
Stars: 33
Forks: 5
Created: 14 Jun 2026
Archived: No

Activity

Last commit: 28 Sep 2026
Latest release: —
Issues open / closed: 0 / 0

The mandatory GitHub GraphQL releases query returned no releases; CHANGELOG.md has an Unreleased section. No release cadence can be established.

Fetched via gh on 15 Oct 2026.

Self-hosting

Methods: source-buildterraformansible
You operate: postgresclickhouseobject-storage

Free Apache-2.0 core plus operator infrastructure costs. Operators supply KVM-capable Linux hosts (or Lima on Apple Silicon for development), identity provider/JWKS, object storage, upgrades and backups. Cloud-only features are database branching, point-in-time restore with a backup browser/retention policies, and connection hardening (IP allow lists, rate limits, pooled URLs). Managed databases are beta; read replicas, storage autoscaling and cross-host volume durability are not shipped. The infrastructure guide states object-storage-dependent agent features are GCS-only with no S3 backend yet: on AWS cross-host replication, WAL archive/failover, UFFD/NBD streaming and seed sync stay disabled, and PGDATA remains host-pinned. This contradicts the broader README claim of GCS or S3-compatible storage. Terraform/bootstrap examples require review and adaptation; Ansible updates an existing fleet rather than provisioning the complete platform. Auth/access-control is intentionally minimal. SDKs and CLI are separately published, not in this repository.

Documentation signals 8/8

SupportedQuickstart
SupportedAPI reference
SupportedSelf-host guide
SupportedChangelog
SupportedOpenAPI
Supportedllms.txt
SupportedExamples
SupportedArchitecture doc

09 Company & presence Facts only, not scored

Company

Headquarters: Not disclosed
Founded: 13 May 2025
Team size: Not disclosed
Hiring: No careers board or hiring status found in checked about/footer sources.

Activity

Last release: 2026-05-31 — v0.5.0 pandastack.ai
Last blog post: — pandastack.ai

Presence 5

Links found on the public surface scanned; not an exhaustive search.

10 Sources & method How this entry was produced

Public surface only

Everything here was read from pandastack.ai's unauthenticated pages, docs, pricing and repository on 15 Oct 2026. Nothing behind a login was used.

Statuses, not scores

Capabilities are pass, partial or fail against a written rubric (features v21). “Not assessed” means the scan predates the key.

Confidence is separate

Each fact carries its own confidence. Low-confidence facts are shown, never hidden, so you can weigh them.

Schema: scan v5
Features registry: v21
Keys tracked today: 61
Assessed on this entry: 61

Something wrong on this page?

Nearby in the atlas

All Sandbox products →