AJNT for Teams

One programmable layer.
Every agent. Every developer.

Your team uses Claude Code, Cursor, OpenCode, and a dozen internal tools. They don't share rules, memory, or models. AJNT puts a single proxy between every agent and every model — so consistency, visibility, and cost controls ship once and apply everywhere.

ConsistencyVisibilityCost savingsPlugin runtime

Your developers

Maya · staff
Claude Code
Devon · platform
Cursor
Priya · ml
OpenCode
Jules · web
internal CLI
AJNT proxy
ActiveContext
+ team rules+ session memory+ model routing+ plugins

Models you pay for

Anthropic · Claude
OpenAI · GPT-5
Google · Gemini 2.5
DeepSeek V4 · direct
Kimi K2.6 · direct
Consistency

Ship a rule once. It runs for everyone.

Your best engineer figures out a context pattern that keeps the agent focused. Today, nobody else gets it. With AJNT, you write the rule once, deploy it to the team, and it applies to every session — Claude Code, Cursor, OpenCode, whatever they pick tomorrow.

Rules are just simple recipes — pin a spec, redact a pattern, inject a convention doc, gate a tool call. No code, no per-developer setup, no agent integration. The proxy already sees every request.

Context injectionRedaction + DLPTool gatingZero-config rollout
Team rule set· web-platform12 active
R
Pin task spec to turn-0
on session:start · prevents drift on long tasks
all agents
R
Redact internal API keys
on message:beforeSend · /sk-[a-z0-9]/i + customer-data
all agents
R
Inject monorepo conventions
on context:beforeAssemble · CONVENTIONS.md · 320 tokens
all agents
R
Require review-ref on prod migrations
on tool:beforeCall · gates db_migrate · escalate to manager
backend
R
Collapse read_file ≥3× duplicates
on context:beforeAssemble · saves 14k tokens / session avg
all agents
deployed to 24 developers · 0 config on their end100% coverage
Visibility

See what your team actually does with agents.

Most managers have no idea. Which prompts are working? Which sessions are burning tokens with nothing to show? Which developer cracked the pattern everyone else needs?

AJNT logs every session at the proxy — model, tool calls, rules hit, tokens, dollars. Inspect any session turn-by-turn. Roll up by developer, by agent, by project. Find what's working and turn it into a team rule with one click.

Session inspectorPer-developer rollupsAudit logsPromote pattern → rule
Team sessions · last 7d
AllCodingResearch
Sessions
1,284
↑ 18%
Rules hit
98.4%
coverage
Saved
$8,420
↑ $1.2k
Maya · staff
42 sessions · Claude Code
$284
Devon · platform
38 sessions · Cursor
$214
Priya · ml
34 sessions · OpenCode
$192
Jules · web
28 sessions · Cursor
$148
Alex · iOS
22 sessions · Claude Code
$132
Cost savings

Route the right work to the right model.

Not every turn needs Opus. A summarization step can use DeepSeek V4 at a fraction of the cost; a real code edit gets the premium model. With AJNT, you set the routing once at the team level — by tool call, by turn type, by agent — and every session follows it.

Allowlist the models your team is allowed to use. Bill open-source models directly through us (DeepSeek V4, Kimi K2.6, GLM 5.1). BYOK for closed providers. Fall back automatically on outages. Compounded with ActiveContext curation, teams typically save another 25–40% on top.

Conditional routingModel allowlistsDirect-bill open modelsAutomatic fallback
Model routing · web-platform3 rules
Cheap path · summarize + read−68%
claude-sonnet-4.5deepseek-v4 · direct
Premium path · code editno change
tool: write_fileclaude-opus-4 · BYOK
Fallback · timeout >30sreliability
any → degradedkimi-k2.6 · direct
August routing · 24 developers$3,180 saved
The plugin runtime

When rules aren't enough, write a plugin.

Every rule above is a plugin under the hood. The real power: write your own. A plugin is a small TypeScript module that subscribes to proxy lifecycle hooks and runs in a sandboxed Dynamic Worker with capability-scoped permissions.

Cross-agent memory that follows a developer from Claude Code into Cursor. Shared knowledge stores a senior can hand off to a junior. Custom guardrails that veto a tool call your security team hasn't approved. Custom routing logic, audit pipelines, prompt scoring — all ship as plugins, not as platform features you wait on us to build.

Authored in-app. Tested live. Published with one click.

session:startcontext:beforeAssemblemessage:beforeSendtool:beforeCallstream:chunkmessage:afterReceivesession:end
plugins/cross-agent-memory.ts
// follow a dev across Claude Code, Cursor, OpenCode
export default definePlugin({
  name: "cross-agent-memory",
  scope: "team:web-platform",
  capabilities: ["kv.read", "kv.write"],
  hooks: {
    async "context:beforeAssemble"(ctx) {
      const mem = await ctx.kv.get(`mem:${ctx.user.id}`);
      if (mem) ctx.prependSystem(mem.summary);
    },
    async "session:end"(ctx) {
      const summary = await ctx.summarize(ctx.transcript);
      await ctx.kv.put(`mem:${ctx.user.id}`, { summary });
    },
  },
});
What teams ship

From day-1 guardrail to bespoke runtime.

Start with a rule, graduate to a plugin when you outgrow it. Same proxy, same surface, same team.

Security · DLP
Redact customer data, automatically
Pattern-match and mask PII, API keys, and internal hostnames before any request leaves your network — across every agent your team uses.
rule
Platform eng
Onboard a junior in one click
Share a senior engineer's session memory with a teammate joining their project. Same plugin, scoped namespace, revocable.
plugin · cross-agent-memory
Finance · FinOps
Hard caps with custom escalation
Set a monthly budget per developer or per project. Trigger a Slack ping at 80%, soft-block at 100%, escalate to manager for override.
plugin · spend-gate
Engineering
Enforce architecture conventions
Inject your CONVENTIONS.md and ADRs into every session prompt — agents stop suggesting React when you use Svelte.
rule · context inject
SRE
Gate production tool calls
Block any db_migrate or kubectl apply that doesn't reference an approved change ticket. Agents stop pretending they have prod access.
rule · tool gate
Manager
Find your team's best patterns
Inspect every session. Find the prompt that consistently lands and promote it into a team rule everyone runs.
inspector → rule
Pricing

Built for teams of 3 to 300.

Per-seat pricing. Team rules, shared rule library, manager dashboards, audit logs, RBAC, GitHub + Google SSO. Higher savings cap per seat than any individual plan.

Larger orgs and regulated environments — we offer SOC 2, self-hosted deployments, dedicated capacity, and custom rule engineering on Enterprise.

Team
$100/ seat / mo
Up to $1,000 saved / seat / mo
  • Team-wide rule sets + plugin runtime
  • Manager dashboards · session inspector
  • Cost per developer reporting
  • Audit logs and RBAC
  • SSO (GitHub, Google)
  • Dedicated Slack channel · 4h SLA
Choose Team

Your team's coding agents,
finally on the same page.

One proxy. One rule set. One bill. Every agent your team will ever use.