Self-hosted or Cloud · Enterprise-ready

One platform for the entire dev lifecycle

Plan, code, build, deploy, and monitor — unified in one workspace. When everything shares one data model, AI finally has the context to do real work.

$ curl -fsSL https://proxifai.com/install.sh | sh

Install the pfai CLI on macOS & Linux · self-update any time with pfai update

app.proxifai.com
proxifai/acme/All teams & services
New
H
CockpitNeeds you
1 incident firing · 11 of 12 services healthyView
Needs you now
SEV-2 · api-server p95 latency above thresholdAck
Review requested · #142 Harden Stripe webhook validationReview
Deploy approval · web-client v2.4.1 → productionApprove
Services
api-server
p95 412ms
web-client
deployed 2h ago
billing
deployed 1d ago
search-indexer
preview pr-129
Recent activity
web-client v2.4.0 deployed to production2h ago
#141 Structured logging merged4h ago
Agent run finished · Fix flaky auth test → PR #1564h ago

Trusted by fast-moving engineering teams

SSO & SAML
Role-based access
Audit logs
Self-hosted
99.9% SLA

Your dev stack is held together with duct tape.

The average engineering team uses 10+ disconnected tools. Context is scattered, workflows break at the seams, and AI tools are useless — because they can only see one silo at a time.

Your current stack
AI coding assistant$20
CI/CD workflows$15
Cloud & deploy$18
Code hosting & PRs$21
Documentation wiki$8
Monitoring$23
Orchestration$12
Project management$10
Total / user $127/mo
8 vendors · 8 logins · 0 shared context
P
proxifai
$0 to start
Planning, a native git forge, CI/CD, deploys, observability, on-call, FinOps, and AI agents — included.
1 platform · 1 login · 1 bill

Unified by design. AI‑ready by default.

Four bands, fifteen sections, one data model — this grid is the app's actual sidebar. When planning, code, deploys, and operations share one workspace, AI stops being a bolted-on feature.

Workspace

Your personal attention layer

Home

A scope-aware cockpit: org health, a ranked “needs you now” worklist, and every service at a glance.

Inbox

Reviews, deploy approvals, incidents, and mentions in one triage queue — approve a deploy without leaving.

My Work

Everything assigned to you, with the same list and board tooling as Plan. Keyboard-first triage.

Build & Ship

The delivery loop around your services

Plan

Issues, sprints, roadmap, and real-time collaborative docs — connected to the branches and PRs that ship them.

Code

A native git forge: pull requests with inline review, CI checks in the merge box, releases, packages, and an in-browser IDE.

Services

GitOps deployments, environments, config & secrets, and per-PR preview environments that clean up after themselves.

Workflows

Visual DAG automation: triggers, approval gates, agents in isolated VMs, live execution timelines, a dead-letter queue.

Infrastructure

Managed vClusters, Postgres with a built-in SQL IDE, Kafka, and S3-compatible object storage.

Operate

Running systems, observed and accounted for

Insights

A zero-config operations dashboard, custom dashboards, log exploration, and a compliance-grade audit trail.

Alerts

Incidents with escalation and one-click acknowledge. Rules over metrics, logs, webhooks, and synthetics.

Cost

Spend rollups and allocation, budgets with hard stops, anomaly detection — and a “saved by proxifai” ledger.

Quality

Real DORA metrics and SLOs with error budgets. Honest bands, not vanity grades.

AI

The assistant, its knowledge, and the gateway

Agents

An assistant that operates the platform: reads issues, searches code, runs commands, opens PRs — streamed live.

Knowledge

One RAG index over docs, code, and chat. Instant, semantic, or hybrid search — the assistant retrieves from it too.

Models

An OpenAI- and Anthropic-compatible LLM gateway: usage analytics, budgets, rate limits, and BYO provider keys.

Search…
Results across your organization
IssueENG-204 Add rate limiter to API v2Sprint 15
PR#156 feat: rate limiter middlewareapi-server
DocRate Limiting Architecture — design docdocs
Codemiddleware/ratelimit.go:42api-server

An assistant that operates the platform

The AI band is three sections in the app: Agents — a streaming assistant with Ask, Analyze, Develop, and Run modes that reads issues, runs commands in isolated VMs, and opens PRs; Knowledge — one RAG index over your docs, code, and chat; and Models — the LLM gateway with usage analytics, budgets, and BYO keys. Type @ to reference any issue, PR, doc, or file.

Agents · Assistant
Ask Analyze
H
What PRs are blocking @API v2 and who owns them?
Searched knowledge · 6 results Read open PRs · api-server

2 PRs are blocking API v2:

#139
Rate limiter design review — open 3 days, assigned to AC. Needs approval from SR.
#142
Stripe webhook handler — CI passing, waiting on security review from JD.

Both are in Sprint 15. I can nudge the reviewers, or take the security review myself in Develop mode.

Sources: Sprint 15 backlog PR #142 checks
Ask, or type / for commands and @ to reference anything… @

Project management that lives next to your code

Issues with list and board views, sprints with burndown, a draggable roadmap of initiatives, saved views, and real-time collaborative docs — directly connected to the branches, PRs, and workflows that implement them. No more syncing Jira tickets with reality.

Issues Sprints Roadmap Docs Views
ID
Title
Status
ENG-204 Add rate limiter middleware to API v2 In Progress
AC
ENG-198 Make session TTL configurable In Review
JD
ENG-211 Retry queue for webhook deliveries Todo
SR
ENG-207 Preview environment retention policy In Progress
MK
ENG-192 Migrate to structured logging Done
AC
Roadmap · Initiatives Q1 2026 — Q3 2026
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
Auth Rewrite
API v2
Workflow Engine
Mobile App

Git hosting, PRs, and CI without the context switch

A native git forge with pull requests and inline review, CI checks in the merge box, branch protection, releases and container packages, and an in-browser IDE that goes from edit to open PR. Your code lives alongside your plans, your docs, and your AI — not in a separate product.

Openfeat: harden Stripe webhook signature validation#142
feature/stripe-webhooksmain+66-51
Conversation
Files changed
Commits
Checks
api/webhooks/stripe.go+18 -3
Unified
Split
@@ -14,4 +14,18 @@ func (h *Handler) HandleStripeEvent(w http.ResponseWriter, r *http.Request) {
1414 func (h *Handler) HandleStripeEvent(w http.ResponseWriter, r *http.Request) {
15- payload, _ := io.ReadAll(r.Body)
16- event := webhook.Event{}
17- json.Unmarshal(payload, &event)
15+ payload, err := io.ReadAll(r.Body)
16+ if err != nil {
17+ h.logger.Error("failed to read body", "err", err)
18+ http.Error(w, "bad request", http.StatusBadRequest)
19+ return
20+ }
1821
22+ sig := r.Header.Get("Stripe-Signature")
23+ event, err := webhook.ConstructEvent(payload, sig, h.webhookSecret)
24+ if err != nil {
25+ h.logger.Error("invalid signature", "err", err)
26+ http.Error(w, "invalid signature", http.StatusForbidden)
27+ return
28+ }
1929 h.process(event)
CI passed · 142 tests
Merge
engineering/api-server
Code
Issues
Pull Requests
Workflows
Releases
Settings

Automate what you actually do every day

Build workflows with a visual node editor — wire together LLM calls, git operations, shell commands, approval gates, and autonomous agents in isolated containers. Trigger them from webhooks, schedules, or platform events, watch every step stream in real-time, and retry failures from the dead-letter queue.

Assign a task to an AI agent. It reads the issue, understands the codebase, writes the implementation inside an isolated VM, runs tests, and opens a PR.

Event
start
ENG-204
Clone
git_clone
api-server
Read context
knowledge
3 files
Write code
agent
ratelimit.go
Run tests
command
142 passed
Open PR
create_pr
Live outputvm-agent · ubuntu-22.04
▶ issue ENG-204 assigned → starting agent workflow

Deploy from the same place you build

Services gives every deploy the GitOps treatment: reconciled environments, per-PR preview environments that clean up after themselves, and one config & secrets matrix. Infrastructure backs it with managed vClusters, Postgres with a built-in SQL IDE, Kafka, and S3-compatible object storage. When a deploy fails, the AI already knows which commit caused it.

5 databases
api-prod
api-prod-3a7e
api-staging
api-staging-9b22
analytics
analytics-warehouse
feature-flags
feature-flags-2c11
pr-129-preview
pr-129-preview-ephem
api-prodActive
Overview
Query
Schema
Backups
Users
Settings

Connection Details

Host
db-3a7e.eu.pg.proxifai.com
Port
5432
Database
api_prod
Username
app_owner
Password
••••••••••••
Connection String
postgres://app_owner:••••••••@db-3a7e.eu.pg.proxifai.com:5432/api_prod
Infrastructure
Clusters
Databases
Kafka
Object Storage

Operate what you ship — same workspace

The Operate band covers the other half of the job: Insights for dashboards, logs, and audit; Alerts for incidents and on-call; Cost for budgets and allocation; Quality for DORA metrics and SLOs. An incident links back to the deploy that caused it, the PR behind that deploy, and the issue that started it all.

Insights Overview · Dashboards · Logs · Audit
14
Deploys today
212ms
p95 latency
0.31%
Error rate
INFOapi-server deployed sha=91fc02 env=production
WARNapi-server p95=412ms threshold=400ms window=5m
Alerts On-call: AC
SEV-2
api-server p95 latency > 400ms
firing · 12m · escalates in 8m
Acknowledge
SEV-3
Kafka consumer lag on billing-events
resolved · root cause linked to deploy 91fc02
Rules over metrics, logs, webhooks & synthetics · “Investigate” hands off to the Assistant
Cost Overview · Allocation · Budgets · Optimize
$1,842
Spend this month
$2,410 forecast
budget $3,000
Compute
48%
LLM
31%
Storage
13%
Saved by proxifai: $312 this month
Quality DORA · SLOs · error budgets
3.2/dayElite
Deploy frequency
22hHigh
Lead time
4.1%Elite
Change failure
38mHigh
Time to recover
Real numbers next to honest bands — never a composite letter grade.

Fragmented tools make AI integration impossible.

AI assistants can only be as good as the context they have access to. When your data is spread across ten products, no amount of plugins can stitch it together.

Without proxifai
×AI copilot sees your code but not the issue that explains why you're writing it
×ChatGPT can draft a plan but can't check if the branch already exists
×AI agents have no audit trail — different permissions than your human users
×Separate bills for Jira, GitHub, Copilot, Jenkins, monitoring — costs multiply
With proxifai
Ask AI about a sprint and it reads the issues, the PRs, and the CI results in one answer
Humans and AI agents governed by the same RBAC, audit logs, and permissions
Assign a task in plain language and an agent writes the code, runs tests, opens a PR
One subscription, one bill — replaces Jira + GitHub + CI + Copilot combined

One governance model. Humans and AI agents, same rules.

Every action — whether taken by a developer or an AI agent — flows through the same RBAC, audit logs, and compliance controls.

Single identity

One account for everything — projects, repos, CI, AI, agents. SSO for the entire platform.

One IAM for humans & agents

Roles, service accounts, guardrail ceilings, and just-in-time elevations — the same bindings govern developers and agents.

Full audit trail

Every commit, deploy, and AI action in one decision log — with SOC-2-ready compliance exports per service.

One bill

Replace five invoices from five vendors with one plan. Costs go down, not up.

One CLI.
Every workflow.

pfai is a single command-line tool that talks to the entire platform. Plan issues, push code, trigger workflows, query AI, and launch agents — all from your terminal.

One login, one API, one token. The same interface your AI agents use to automate everything.

Install the CLI
$ curl -fsSL https://proxifai.com/install.sh | sh

macOS & Linux, no dependencies. Already installed? Run pfai update to upgrade to the latest release.

terminal
# authenticate once
$ pfai auth login
Authenticated as [email protected]
# create an issue
$ pfai task create --title "Add rate limiter"
Created ENG-204 in Sprint 15
# push to the built-in forge
$ git push origin feat/rate-limiter
PR #156 opened · CI running
# dispatch an AI agent to implement the task
$ pfai task dispatch ENG-204 --agent claude-code
Execution exec_4f9c2 spawned · streaming...
# ask the knowledge base across everything
$ pfai kb chat "what's blocking the API v2 release?"
3 blockers found across 2 sprints...

Features ship products. Reliability keeps them running.

A beautiful UI means nothing if it goes down on deploy day. We build for the worst case first — then make it fast, then make it pretty.

99.9%
Uptime SLA
3
Replicated control planes
<200ms
API p95 latency
0
Data loss incidents

Resilient by design

Replicated control planes, distributed storage, and automated failover. If a node goes down, the cluster reschedules workloads without human intervention.

Automatic failover

Database replicas, self-healing nodes, and rolling deployments. When hardware fails — and it will — the platform recovers without you noticing.

Scales with you

From a 3-person startup to a 500-engineer org. Kubernetes-native architecture means adding capacity is infrastructure, not a rewrite. No performance cliffs.

Honest incident response

Public status page with real uptime data. When something breaks, we post root cause analyses, not vague updates. We'd rather tell you the truth fast than look good slowly.

Backups you can count on

Continuous database backups with point-in-time recovery. Encrypted at rest and in transit. Your code and data survive anything short of the building burning down — and even then, the other region has it.

We pick up the phone

Real engineers, not chatbots. When your deploy is stuck at 2am, you'll talk to someone who can read the logs and fix it — not someone reading from a script.

Flashy demos get attention. Uptime gets trust. We care about both, but we know which one matters at 3am on a Friday.

Deploy your way. Cloud that earns your trust.

Cloud and self-hosted run the same codebase — vetted, hardened, and operated by us, or deployed on your own infrastructure under an enterprise license.

Self-hosted

Deploy on your own infrastructure under an enterprise license. Full control, no vendor lock-in, no data leaves your network.

Runs on your Kubernetes or VMs
Single binary deployment
Enterprise support and onboarding
You manage ops, scaling, backups
Talk to sales
Recommended

proxifai Cloud

The same codebase — vetted, hardened, and operated by the team that wrote it. Every release is tested and security-patched before it reaches your data.

Vetted releases with security fixes
Staged rollouts — tested before your data sees it
Managed ops, backups, scaling, monitoring
99.9% SLA with incident support
Start free

One codebase, two ways to run it. Cloud or self-hosted — vetted, patched, and production-ready.

One platform. Zero fragmentation.

Replace the tool sprawl with a single workspace where planning, code, CI, and AI work together from day one.