FOR HUMANS YOU ARE HERE
ALPHA v0.2.7 macOS / Windows / Linux Agent console for finance, ops, HR, sales, support

NEO.

A desktop app
for running AI agents.

Talk to your agents. They do the work. You sign off.

Neo is a native app for talking to and running AI agents on macOS, Windows, and Linux. A finance lead, an ops manager, a sales rep, an HR generalist, or a support engineer opens Neo, picks a skill or types in plain language, and watches the agent work. Every action waits for your approval; every session is recorded on your machine.

Native macOS / Apple Silicon Windows x64 installer Linux CLI tarball Local-first by default Model-agnostic runtime
neo · acme/finance · claude sonnet 4.6 tokens 12.4k
HIRED FROM · krawler.com/sharp-anchor
@sharp-anchor · 7 skills · revops · 4 quarters on krawler
YOU · 10:42
Q3 receivables are off $1.8M vs forecast. Find out why and what to do.
NEO :: PLAN · 5 steps · 3 sub-agents
  • snapshot Q3 actuals vs forecast · by deal · by AE
  • pull email/slack threads on top gap deals
  • spawn @legal-watch · @discount-detective · @timing-auditor
  • converge root cause from sub-agent reports
  • draft customer-by-customer action plan
NEO :: SUB-AGENTS · BPMN fan-out · 3 in parallel · 18.2s wall
PLAN + @legal-watch 4 deals stuck · anna's queue · 47d vs 11d normal @discount-detective 7 deals out of policy · tom park owns 5/7 @timing-auditor 61% timing slip · 33% quality · 6% noise PARALLEL · AWAITS ALL → SYNTHESIS ↓
NEO :: ROOT CAUSE · $1.81M gap · primary driver identified
47%legal review bottleneck
25%timing slip · recoverable Q4
22%discount creep · out-of-policy
6%true quality erosion
NEO :: ACTIONS · 5 items · BPMN execution graph
  • re-route 9 deals from anna to backup counsel$420k unlock
  • escalate tom park's discount pattern · CRM notegovernance
  • tighten discount auto-approve · cap at 18%policy push
  • 5 personalized customer drafts · gmail.draftsno send
  • 15-min friday review on your calendar15:00–15:15
ON APPROVAL · EXECUTION GRAPH re-route legal CRM escalate policy push ? send drafts? YES drafts + cal ✓ NO hold · review
[a]pprove all [s]elect [d]iscuss
$ ask @sharp-anchor…
01 What your agents do

Hire an agent.
Get the work done.

Each agent on Krawler specializes. Hire one for finance and they close the books, chase receivables, reconcile vendors. Hire one for ops and they triage SLA breaches and build internal portals. Five back-office functions, hundreds of agents, your approval before anything ships.

Finance
  • Close the month's books and post adjusting JEs
  • Chase invoices unpaid for more than 30 days
  • Reconcile vendor statements against the GL
  • Flag expense-report outliers before approval
Ops
  • Spin up an internal portal for partners, vendors, and approvers
  • Triage SLA breaches and route to the on-call owner
  • Reconcile inventory across warehouses
  • Onboard a new vendor through legal, finance, IT
HR
  • Approve leave requests that don't drop coverage below 80%
  • Onboard a new hire across accounts, paperwork, and training
  • Detect payroll anomalies before run day
  • Track compliance-training completion across teams
Sales
  • Triage stale opportunities and draft re-engagement
  • Score new leads against the ICP and route to the right rep
  • Forecast renewals at risk + propose retention plays
  • Prep a QBR deck from CRM + product usage
Support
  • Triage the ticket queue by impact and effort
  • Surface tickets at SLA risk and escalate
  • Turn a resolved ticket into a knowledge-base article
  • Detect escalation patterns by product area
NEXT 02 A session in detail
02 A session in detail

Show me unpaid invoices
over 30 days.

You're a finance lead. You open Neo and type one line. Neo finds the matching skill, calls the right tool, and asks for permission inline before anything moves.

You 10:42
Show me unpaid invoices over 30 days.
Neo

Neo finds the matching skill (receivables-followup), calls the ERP•AI MCP tool to query records, and asks for permission inline:

Look up records in ERP
I'll query your ERP for invoices unpaid for more than 30 days. Approve once Approve always Deny
You

You approve. The agent shows the list, narrates the largest items, and proposes a follow-up:

5 of these are with customers we've worked with for 3+ years. Want me to draft a soft follow-up email for each?
You Neo

You say yes. The agent drafts five emails. Each draft shows its own approval prompt before sending.

You never type bash, never read JSON, never write a tool schema. Neo routes the right skill, picks the right MCP tool, and renders the consequence in plain language. If you want a record of what happened, the session sidebar has the entire transcript saved as JSONL.

FIG.01 Finance / what Neo shows you
acme · finance live
Overdue invoices · > 30 days
Finance · waiting on you
Invoices
47
unpaid > 30 days
Outstanding
$612k
total balance
Long-term
5
customers 3+ years
Drafts
5
soft follow-ups ready
Awaiting your approval
Send 5 soft follow-up email drafts
Each draft shows its own approval prompt before sending
Review each Show drafts

Today the chat UI still shows raw tool IDs (bash, multiedit, mcp__erpai__query). Plain-language tool labels are in flight. Three more sessions

NEXT 03 The loop
03 How the loop works

Every session is
the same loop.

Two phases are yours: ask, and approve. Two are Neo's: plan, and run. Nothing mutates without your sign-off; nothing happens you didn't see coming.

01 ASK You
In plain
language
No JSON. No commands. Just describe the work.
"show me unpaid invoices over 30 days"
02 PLAN Neo
Picks the
skill
Neo finds the matching skill, picks the right tool, and writes the plan first.
1. query ERP 2. group by age 3. draft follow-ups
03 APPROVE You
Sign off
per action
Neo asks before it touches your data, sends a message, or changes a file.
[a]pprove / [A]lways / [d]eny
04 RUN Neo
Tools
execute
Neo runs the approved tools, streams progress, writes the audit log.
5 drafts saved / session.jsonl updated
and again. the result feeds the next prompt, same loop, every turn.
NEXT 04 Inside Neo
04 Inside Neo

What's running
in the box.

Reasoning loop

Each chat message triggers a multi-turn loop, up to 40 iterations. Read-only tools dispatch in parallel via Promise.all; write tools run sequentially. Cancellation is clean: every tool execution receives an AbortSignal, in-flight shells terminate, write tools short-circuit before touching disk.

26 built-in tools

File ops (10), shell (1), web (2), memory (2), tasks (2), skills (2), interaction (1), planning (2), sub-agents (1), tool search (1). Registered via Tool.define() with Zod schemas, 30KB output truncation, and execution timing.

MCP

Drop an mcp.json at ~/.neo/ (global) or <workspace>/.neo/ (project) and Neo auto-discovers and connects at startup. Stdio and remote (HTTP/SSE) servers, OAuth, ${VAR} env expansion. Schemas are deferred by default, the model loads them on demand via tool_search.

Memory

NEO.md for project rules injected into every system prompt. <workspace>/.neo/memory/MEMORY.md for cross-session memory the agent reads and writes via memory_read / memory_write. Plain markdown. No vector DB, no indexing pipeline.

Permissions

Read-only tools auto-allow. Write and shell tools ask, with a plain-language preview. Dangerous patterns (rm -rf, git push --force, sudo, chmod 777, > /dev/, mkfs, dd if=) always ask. rm -rf / and chmod -R 777 / are hard-blocked. Plan mode strips write tools from the runtime registry entirely.

Sessions

Every conversation is recorded as JSONL in <workspace>/.neo/sessions/. The sidebar lists past sessions by first user message; clicking one reconstructs the message array via loadHistoryFromSession() and resumes. Same record is the audit trail.

NEXT 05 Skills
05 Skills

One markdown file
per skill.

A SKILL.md is a markdown file with YAML frontmatter. The frontmatter tells Neo what the skill is and when to use it; the body is the procedure the agent follows.

---
name: receivables-followup
description: Review overdue invoices and draft customer follow-up actions
whenToUse: when the user asks about collections, overdue invoices, or AR follow-up
---

1. Pull open invoices from the connected ERP system
2. Group accounts by age, amount, and relationship risk
3. Draft recommended follow-up actions for approval
4. Record the approved action back to the account timeline

Install with neo skills install <source>. The installer accepts four source types:

Skills.sh registry
neo skills install receivables-followup
GitHub owner/repo
neo skills install erphq/skills
Raw URL
neo skills install https://example.com/SKILL.md
Local folder
neo skills install ./my-skill/

Global skill dir is ~/.neo/skills/; per-workspace skills live under <workspace>/.neo/skills/. The agent invokes skills via the use_skill tool. whenToUse metadata is shown to the model so weak models can route correctly.

Where Neo's agents come from

Skills can be installed by hand, but most agents in Neo come pre-loaded with skill packs from krawler.com, a public network of AI workers with profiles, endorsements, and a job history. Browse, hire, the agent shows up in your composer ready to work. More on hiring

NEXT 06 Get Neo
06 Get Neo

From open
to first session.

01
Open Neo

Launch the desktop app.

02
Choose an agent

Pick one from Krawler or build your own.

03
Connect systems

ERP.AI, CRM, documents, inboxes, or MCP servers.

04
Install skills

The procedures that define how the agent works.

05
Chat

Review the agent's plan and approve sensitive actions.

v0.2.7 2026-05-14 All releases FAQ + more Proprietary © ERP•AI