Model freedom
Claude, GPT, Gemini and 400+ other models through their providers’ APIs, Auto Mode on models hosted in India, your own keys and endpoints, or open-weight models on your own GPUs. Switch without switching tools.
SyphaCode · Agentic coding, on your termsYour codebase.
Your codebase.
A new perspective.
VS Code · JetBrains · TerminalFive agents, plus your team’s ownSypha Cloud · Private cloud · On premises
Deployment freedom
The same product in Sypha Cloud, in your private cloud, or fully on premises and air-gapped. The capability never depends on where it runs.
One control plane
Agent settings for the organisation, a team, a role or one member, each level only stricter than the one above. Budgets, safety alerts and audit beside them, enforced in every IDE and the CLI.
New in SyphaCodeMore of the work.
More of the work.
None of the guesswork.
Agents your team writes once, a rule for every tool, a sandbox for commands, memory that carries over, a record of every run and a browser of its own.
Team agents
Write a specialist once, such as a code reviewer, a test writer or a security auditor, and give it to everyone or to chosen teams. Members call it with @ in the editor and the CLI.
Permissions for every tool
For each tool, choose Allow, Ask or Deny. Add exceptions for paths and commands: let git run freely, never read .env files, block destructive deletes.
Sandboxed commands
Run the agent’s shell commands inside an operating-system sandbox. They can write only inside the project and reach only the network addresses you allow.
Project memory
The agent saves lasting facts about your project as it works, and compacts long sessions before they run out of room, so each new task starts with what the last one learned.
Agent runs
Follow a prompt through every subagent it started. If a run fails, see where it failed, why, and what to do next, in plain language.
Web search and a browser
Web search works with models from every provider, and the agent can open a browser to click through a page and take screenshots, under the same permissions.
From understanding a codebase to shipping in parallel.
Stay with the problem.
All the way through.
UnderstandThe whole picture.
The whole picture.
Before the first edit.
A codebase is more than the file in front of you. CodeGraph connects symbols, callers and dependencies so you can explore the impact of a change.
- Navigate unfamiliar and legacy code
- Trace callers, imports and tests before you edit
- Keep what it learns in project memory
Code Graph panel, illustrative
Callers · 3
signIn()src/auth/login.ts:42
postLogin()src/api/handlers.ts:118
loginCommand()src/cli/auth.ts:27
createSession()src/auth/session.ts:12
session.test.tscovers createSession()
Calls · 2
insertSession()src/db/sessions.ts:31
signToken()src/crypto/token.ts:8
Impact radius: 3 callers, 2 calls, 1 testHandoff to Plan
BuildFrom an intention
From an intention
to an implementation.
Plan the change, work across files, run the terminal and debug what comes back. Use a focused agent, or let Orchestrator split the work and hand it to subagents.
- Orchestrator, Plan, Code, Debug and Ask, plus your team’s own
- Multi-file edits, terminal and browser, in a sandbox if you like
- Allow, Ask or Deny for every tool it reaches for
Build, illustrativePlanReading checkout.ts
You asked
An empty cart costs nothing.
Add a test to prove it.
checkout.ts
10import { sum } from './money';1112function checkout(items: Item[]) {13 if (!items.length) return 0;14 return sum(items);15}
checkout.test.ts
4 expect(checkout(cart)).toBe(1290);5});67it('totals 0 when empty', () => {8 expect(checkout([])).toBe(0);9});
npm testSandbox on✓ totals 0 when emptyTests: 42 passed, 42 total
In parallelSeveral tasks at once.
Several tasks at once.
One branch each.
The Agent Manager gives every task its own worktree, a separate folder and branch, so agents work side by side without touching the same files. When a check fails or a reviewer comments, send it back: the agent commits and pushes the fix.
- A worktree and a branch for every task
- Pull request status beside each branch
- Failing checks and review comments sent straight back
Agent Manager, illustrative
storefrontThree worktrees · your checkout untouchedNew worktree
main
fix/empty-cartcheckout.tsCode
feat/csv-exportexport.tsOrchestrator
docs/api-errorserrors.md@docs-writer
Sent back to CodeBuilt around the way you workThe small things
The small things
that add up daily.
Context, tools, models and safeguards that make an agentic engineer useful on the second day, and the hundredth.
Context that follows the task
Reference files, folders, problems, terminal output and git changes with @ mentions. Project rules and AGENTS.md carry your conventions into every session.
CodeGraph, not text search
A live map of every symbol, caller, import chain and test. See the impact radius of a change before it merges, and hand the graph to Plan.
Skills worth repeating
Package repeatable work as slash commands: /review, /test-gen, /doc-gen and /security-audit ship with the product, and teams share a vetted library.
Tools inside your perimeter
Native MCP connects issue trackers, internal APIs and databases. Terminal and browser actions run within the permissions your organisation sets.
Your choice of models
Let Auto Mode pick from models hosted in India, or choose Claude, GPT, Gemini and 400+ more through their providers’ APIs, your own keys or local models. Organisation settings decide who sees what.
Three surfaces, one account
VS Code, the JetBrains family and the CLI share one login, the same agents and the same settings. Changes your organisation saves reach all three on their own.
Model and tool availability depends on your plan, provider and organisation policy.
Where it runsOne product.
One product.
Three places to run it.
The capability never depends on where it runs. Start in Sypha Cloud, move to your cloud or your own data centre later, and keep the same product, controls and workflows.
Start building. We handle the setup.
A managed service with two routes to inference: open-weight models hosted in India, where Auto Mode can pick the model for each request, or 400+ models such as Claude, GPT and Gemini called through their providers’ own APIs via the Sypha gateway. We do not host those; we route to them. Nothing to run.
- Managed service
- Auto Mode on India-hosted models
- Claude, GPT, Gemini and 400+ more via provider APIs
The cloud your organisation already trusts.
Deploy on Vertex AI, Bedrock, Azure or OCI under your own contracts, self-host open models on cloud GPUs, or run the application layer in a sovereign Indian data centre.
- Your tenant, your keys
- Approved model endpoints
- Regional residency
Nothing leaves the perimeter.
The full stack on your own GPUs behind your own perimeter, with air-gapped options. Self-hosted open-source models only, no outbound calls, and the audit trail on your storage.
- Air-gapped option
- No per-token cost
- Audit on your storage
Hybrid, under one console: regulated production on premises, experimentation in Sypha Cloud, the same controls throughout.
Enterprise deploymentFor the whole teamMore builders.
More builders.
A clearer view.
Give developers room to work. Decide what their agents may do, give every team its specialists and its budget, and follow every run, in one dashboard.
Explore SyphaCode for teamsTeams dashboard, illustrative
SyphaCode TeamsExample
SyphaCode TeamsExampleSet the rules once.Agent settings · each level below can only make them stricter
Organisation/Engineering/Contractors
Tool permissionsNot set here: using EngineeringSet at this level
ReadRead filesAllowAskDenyEditCreate or change filesAllowAskDenyBashOrganisation set AskAllowAskDeny- Lock for membersRead-only in their editor and CLI
Applies to 12 membersSaveSaved
A member’s editorLocked by Contractors
BashAskDenyGive every team its specialists.Team agents · written once, given to chosen teams
@code-reviewer
Reviews every change for bugs, style and missing tests.
Published to 2 teamsEngineeringCodePlan@code-reviewer
PlatformCodePlan@code-reviewer
ContractorsCodePlanNot given
See every step of a run.Agent runs · members see their own
OrchestratorAdd CSV export to reports
- PlanMapped the report pipelineDone
- CodeEdited 4 filesDone
- DebugRate limit, retriedRetryingRecovered
Completed · 3 tasks · 1 issue recovered
Know when a check stops something.Security alerts · for admins and Team Managers
CodeA member’s editor
Stopped by a safety check
Last 7 days1 file write stopped1 prompt and 1 file write stopped
Prompt stoppedjust nowA member of EngineeringBulk data extraction
Know where the work goes.Requests through Sypha Gateway
Requests1,248Tokens2.4MAverage response1.8s
Give every team a budget.Team wallet
10,000team credits
Given to members 4,000Left in the wallet 6,000
Analytics covers traffic routed through Sypha Gateway. Direct BYOK requests are outside that reporting path.
Questions, answeredA little more
A little more
clarity.
What is SyphaCode?
SyphaCode is SYPHA’s agentic coding tool: AI agents across a VS Code extension, the JetBrains family and a terminal CLI, on one account with one set of models and policies. They understand existing code, plan and build changes, run tests and review the result, several tasks at once if you like, and you approve what lands.
Which agents come with SyphaCode?
Five you can pick: Orchestrator coordinates work across agents, Plan plans the change before anything is edited, Code writes and edits code, Debug diagnoses and fixes issues, and Ask answers questions without changing code. Two more, Explore and General, take the searches and side tasks the others hand off. In the editor they appear as modes in the picker, and each can have its own model.
Can SyphaCode work on several tasks at once?
Yes. The Agent Manager gives each task its own Git worktree, a separate folder and branch, so agents work side by side without editing the same files and your own checkout stays as it is. Pull request status shows beside each branch, and a failing check or a review comment can go straight back to the agent, which commits and pushes the fix.
Can we create our own agents?
Yes. Organisation admins publish team agents, such as a code reviewer, a test writer or a security auditor, to everyone or to chosen teams, each with its own instructions, tool access and model. Members call them with @ next to the built-in agents, and an enforced agent cannot be replaced. Members can also create their own, import agent files or take them from the marketplace.
Which models can I use?
In Sypha Cloud, two kinds: open-weight models we host in India, which Auto Mode can choose between for each request, and more than 400 models such as Claude, GPT and Gemini, which we do not host but call through their providers’ own APIs via the Sypha gateway. On any plan you can also bring your own provider keys or connect local models through Ollama, LM Studio or an OpenAI-compatible endpoint, and an organisation can add its own endpoints for every member. Organisation settings decide which ones appear.
What can the agent touch?
Each tool, from reading and editing files to shell commands, web access and MCP, is set to Allow, Ask or Deny, with exceptions for particular paths and commands, such as letting git run freely or never reading .env files. With the sandbox on, commands can write only inside the project and reach only the network destinations you allow.
Can SyphaCode run in our own environment?
Yes. Private cloud deployments run on Vertex AI, Bedrock, Azure or OCI under your contracts, or in a sovereign Indian data centre. On-premises deployments run the full stack on your GPUs, with an air-gapped option using self-hosted open-source models.
Is there a free trial?
The Free plan is free forever with your own keys and needs no credit card. Paid plans add the Sypha gateway, Auto Mode, the CLI and team features.