[>] FOR DEVELOPERS WHO CODE WITH AI AGENTS

STOP YOUR AGENT
FROM BREAKING YOUR CODE.

YOUR AGENT GREPS, READS 30 FILES, AND STILL MISSES THINGS.
ARGOSBRAIN GIVES IT EXACT ANSWERS IN MS.

ArgosBrain turns your codebase into a deterministic graph your AI agent can query directly. No more grep loops, no more re-reads, no more "I think this is where it lives". Just exact answers, in ms, at zero token cost.

Works with Claude Code · Cursor · Codex CLI · Copilot · any MCP-compatible client
🦀 Zero-panic Rust core Runs in background < 50MB RAM footprint Branch-aware — query branch & main side-by-side
// What you just saw

Claude reads files to remember. ArgosBrain remembers, so Claude doesn't have to.  Same prompt, same repo, same model.

// What this looks like in production

Uber just ran out of 2026 AI budget.
They didn't have to.

"Uber has exhausted its full 2026 AI token budget and is managing costs by deploying expensive frontier models for initial development, then switching to cheaper or open-source alternatives at scale."

@TheDeepDiveFeed · publicly disclosed · 2026

UBER applied to ArgosBrain math
Without ArgosBrain · 2026 budget
REPO RE-READ TAX · 73%  ←  this is what burns the budget
ACTUAL WORK · 27%

→ Budget runs out by Q3. Forces downgrade to cheaper models at scale.

With ArgosBrain plugged in
ACTUAL WORK · 27%
73% RECLAIMED · runway extended

→ Same dollar budget. 3.7× more agent work. Frontier models stay on the entire pipeline.

// re-read tax
73%
of agent input tokens are redundant re-reads of files already loaded earlier in the same session. Eliminated by graph lookup.
// budget multiplier
3.7×
effective AI runway on the same dollar budget. Same models, same prompts, same workflow — just the graph in front of them.
// per query
$0
retrieval cost. The engine is in-process Rust, runs locally, and never calls an LLM on the read path. Forever.

The choice isn't "frontier model vs cheaper model". It's "agent that re-reads vs agent that remembers". Drop the re-read tax and you don't have to downgrade anything.

↳ Methodology, raw data, and the 30-day field study these numbers come from: The Re-Read Tax →

// What ArgosBrain is, exactly

A local index of your code, queryable like a database.

ArgosBrain is a local structural graph of your codebase — every symbol, every call, every import — that your coding agent queries via standard MCP. Claude Code, Cursor, Codex, Cline, Aider — all talk to it natively with zero changes to your workflow. You install it once, and your agent stops re-reading the same files for the rest of your life.

// 01
One install
Sign in with GitHub. One copy-paste line per agent.
// 02
Zero workflow change
Your Claude Code, Cursor, Codex prompts stay exactly the same.
// 03
Local & free
Runs on your machine. Free tier never expires.
// The 73% chunk

73% of your Claude Code bill is your agent re-reading code it already read.

That's the chunk ArgosBrain eliminates.

STATIC · 17K · 16%
REPO CONTEXT · ~80K · 73%  ←  ArgosBrain eliminates this
HIST · 9%
2%
tool defs
the chunk we eliminate
chat log
code
01 · STATIC OVERHEAD
~17K tokens · 16%
System prompt (2.5K)[3] + built-in tools (14-17K)[2] + MCP tool schemas (0.5-7K)[4]. Loaded on every message.
→ We can't make this zero. It's how Claude Code works.
02 · REPO CONTEXT  ←  the bleed
~80K tokens · 73%
Files your agent reads to answer the question. Grep output that stays in context for the rest of the session. Anthropic confirms: "Claude re-reads the entire conversation from the top on every message."[5]
→ THIS is what ArgosBrain eliminates. Graph lookup = 0 tokens.
03 · HISTORY + YOUR CODE
~10-12K · ~11%
Conversation history (~9%) — every prior message; message 50 costs more than message 5.[5] Code output (~1-2%) — your prompt + the code the agent writes.
→ History shrinks 30-50% indirectly. Code output you keep paying for — that's the point of an agent.

How much we save, by repo size

Honest claim ready to fact-check.

Repo size Static Repo context History Code Net savings
Side project (10K LOC)17K · 45%18K · 47%2K · 5%1K · 3%~35-45%
Mid SaaS (50K LOC)17K · 28%40K · 65%3K · 5%1K · 2%~55-65%
Large product (250K LOC)17K · 15%80K · 73%10K · 9%1K · 1%~70-75%
Monorepo (1M+ LOC)17K · 8%180K · 85%12K · 6%2K · 1%~80-85%

The bigger your repo, the more we save. On a 250K-LOC project we cut roughly 70%. On a monorepo, closer to 85%. We can't make the 16% Claude Code system overhead disappear — that's Anthropic's architecture, not ours.

Token-bleed calculator

10K50K250K1M
Your team is burning an estimated:
$1,480
/ month on retrieval tokens
$17,760
/ year on grep + read + summarize
~11M
tokens/day ArgosBrain returns in 0
With ArgosBrain plugged in: ~$0.06 / query. That's $12,400+ saved on a team of 1 in year one.
Install — free →

Defaults from Anthropic's published averages: $6/dev/day Claude Code average, $13/dev/day enterprise, top 10% up to $30/day.[6][7]

Agent token burn is one of 14 services we provide. See the other 13 →
Benchmarks

We couldn't find a benchmark for AI code memory. So we built it.

The existing options — LongMemEval, RULER — measure generic recall on chat transcripts. None of them touched actual codebases. We authored ours and put it under MIT.

LongMemCode kubernetes-2k is our open-source corpus of 1,456 structural scenarios across 8 categories on the real Kubernetes v1.32.0 codebase (333 MB Go source, 38,771 symbols, 232,756 call-graph edges) — symbol existence, caller enumeration, reachability, naming convention, blast radius, plus 100 real bug-fix commits mined from git history. Every scenario has a deterministic ground truth derived from the actual AST. No LLM judge. Either the answer matches the AST or it doesn't.

Yes, we built it. Yes, our engine runs against it. But the runner, the scenarios, and the per-scenario raw results are public — anyone can clone, run on their own laptop, and try to break the numbers. Reproducibility is the only honest answer to "but you graded yourselves." Source: github.com/CataDef/LongMemCode

New · 2026-04-25 · Case study
We pointed an AI at Kubernetes 1.32.0. Twice. Total cost: 44¢.

17,171 files. 303,722 symbols. 2,245,124 call-graph edges. Two runs, two skills. Security audit: 22 sink categories triaged, zero reachable critical findings, library gaps disclosed publicly. 70 seconds, $0.33. Architectural code tour: the AI deduced the engineering culture — spine, heartbeat, naming convention modulo machine-generated noise. 6 seconds, $0.11.

Read the case study →  ·  Read the paper →

// Your notes + your agent's index

Obsidian is great. ArgosBrain solves a different problem.

A lot of devs we talk to already keep notes about their code in Obsidian, Notion, a wiki, or a CLAUDE.md file. That's a good habit — keep it.

ArgosBrain isn't a replacement for any of those. It's a different layer entirely: instead of storing what you think about your code, it stores what your code is, and your agent queries it directly via MCP. The two tools stack — they don't compete.

Obsidian (and similar) ArgosBrain
JobYour second brain — thoughts, designs, decisionsYour agent's code index — symbols, callers, types
Who writes the dataYou, when you sit down to thinkYour repo, automatically on every commit
Who reads itYou (and occasionally your agent, if you paste)Your agent, on every prompt, via MCP
Best forPRDs, design docs, journal entries, learningsCode structure questions, refactoring, call graphs
Stays in sync with codeYou maintain itFile-hash invalidation re-indexes only the diff
Costs tokens to queryYes — pasting notes loads them into contextNo — 0 tokens, sub-ms graph lookup
Use Obsidian to think.
Use ArgosBrain so your agent doesn't have to guess.
They're better together.
// And what about CLAUDE.md?

CLAUDE.md is narrative. ArgosBrain is structural. They stack.

CLAUDE.md is a markdown file you put in your repo root. Claude Code reads it on every session and injects it into the agent's prompt as project context. It's the place for your dev journal — preferences, conventions, the things you want the agent to always know.

Keep writing those. Just understand what they're good at — and what they're not.

// What CLAUDE.md is great for

  • "Always use Tailwind, never inline styles."
  • "Tests live in /spec, run with vitest, never jest."
  • "This project uses pnpm. Never run npm install."
  • "PRDs are in Notion at notion.so/our-team/prds."
  • "When deploying, always check the staging diff first."

Preferences and conventions. The kind of thing that doesn't change every commit.

// Where CLAUDE.md breaks down

It can't answer questions that depend on the current state of the code. Three concrete examples — same scenario, what each can and can't do.

Example 01 · A QUESTION
user → "Where is verifyToken called?"
CLAUDE.md
Doesn't know. You'd have to manually maintain a "Functions and their callers" section — which goes stale the moment you refactor.
✗ no answer
ArgosBrain
✓ 6 callers in 0.4ms
 1. middleware.ts:18  requireUser
 2. middleware.ts:54  requireAdmin
 3. handler.ts:127    POST /api/graph
 4. handler.ts:241    DELETE /api/repo
 5. socket.ts:88      ws upgrade
 6. cron/cleanup.ts:33 background job
Example 02 · A REFACTOR
action → You rename verifyToken to validateToken and commit.
CLAUDE.md
Stays out of date until you manually edit it. Anyone reading it a week from now still sees verifyToken. The agent gets stale instructions and may invent a wrong API.
✗ silent staleness · human action required
ArgosBrain
File-hash invalidation triggers re-indexing on next ingest (typically <5s on a clean diff). The graph reflects validateToken the moment your file is saved.
✓ auto-current · no human action
Example 03 · THE COST
scenario → Your project has a 5KB CLAUDE.md. You run 60 queries/day.
CLAUDE.md
Injected into the agent's context on every message. 5KB ≈ 1,250 tokens × 60 queries = 75,000 tokens/day just from CLAUDE.md.
✗ ~$5-7/month per dev, every dev, every day
ArgosBrain
Stays on disk. Agent calls argos.list_callers() on demand and gets only the answer it needs — file:line of 6 callers, ~30 tokens.
✓ 0 tokens for the structural lookup itself

// Field proof · one developer, same project, one day apart

Tool-use histograms from two real Claude Code sessions on the same Next.js codebase (~400 files). The only variable: whether the project had a CLAUDE.md telling Claude to reach for ArgosBrain first.

Before — no CLAUDE.md · 1 237 turns
189  Edit
177  Read
146  Bash
127  Grep         ← every code question
  9  Glob
  9  Write
  6  ToolSearch
  2  AskUserQuestion
  0  mcp__argos__*    ← MCP installed, never called
After — CLAUDE.md v3 · 161 turns
 26  Bash
 24  Read
 23  Edit
 16  TodoWrite
 13  mcp__argos__symbol_exists
  8  mcp__argos__search
  3  ToolSearch
  1  mcp__argos__ingest_codebase
  0  Grep             ← agent trusts structure now

In the second session, search also surfaced four SSRF call-sites the first session's Grep had missed — they lived outside the directory the audit was pointed at, reachable only via Causal edges in the call graph.

Keep CLAUDE.md for what humans write — preferences, conventions, narrative.
Let ArgosBrain handle the facts the compiler already knows — symbols, callers, types, paths.
Use them together. They never compete on the same field.
Field report — Claude Opus 4.7

The trophy cabinet. Opus 4.7 live reviews.

We didn't write these reviews. Claude Opus 4.7 did — unprompted — during a live 1 237-turn coding session on a production Next.js SaaS. The agent graded ArgosBrain against Grep and RAG on real jobs it had to do that day. Below are its seven own-word assessments, unedited beyond light trimming. The eighth card (multi-modal) ships in v0.2 — it arrived after the review, so it's ours, labelled as such.

01 / RECALL

The SSRF Discovery

High-recall via call-graph

"The initial audit scoped src/app/api/ and found two SSRF sites. ArgosBrain surfaced four more in src/lib/services/ — the agent had to follow causal edges across directories Grep wasn't pointed at."

Claude Opus 4.7 · dogfood session · 2026-04-22

2× RECALL VS. GREP
Grep is scoped by the pattern you give it — miss the directory, miss the vulnerability. Mem0 / Zep don't model code structure.
02 / PRECISION

The Buffer Check

Type-safety via exact signature

"Argos returned a CLEAR match: uploadVideoToTikTok(videoBuffer: Buffer, …) takes a Buffer, not a URL. The agent was about to patch the call site as if it accepted a URL — that retrieval prevented a silently-broken commit."

Claude Opus 4.7 · dogfood session · 2026-04-22

PREVENTED A BAD COMMIT
Naive RAG ranks by semantic similarity; a lookalike function can outrank the real one. The signature gets lost in the vector distance.
03 / CONFIDENCE

The RLS Deletion

Architectural confidence via definitive-no

"Before deleting an RLS-bypassing route I thought was dead, I asked Argos for its callers. It returned NO_CONFIDENT_MATCH — exhaustive over the ingested codebase. Not 'I didn't find any'; 'there are none.' Deleted with confidence, no regression."

Claude Opus 4.7 · dogfood session · 2026-04-22

SAFE DEAD-CODE CUT
Grep can't prove negatives. RAG returns three weak-confidence matches instead of admitting nothing exists.
04 / REUSE

The Endpoint Reuse

Anti-spaghetti via cross-session memory

"I was about to write a new handler. Argos pulled up the existing one from an older session — same behaviour, already tested. Saved me a duplicate route and the tech debt that comes with it."

Claude Opus 4.7 · dogfood session · 2026-04-22

NO DUPLICATE HANDLERS
Cursor's native index is per-session and closed. Grep finds text matches but can't tell you they're functionally equivalent.
05 / STYLE

The Pattern Matcher

Style consistency via structural tools

"Before adding a new admin check, Argos surfaced ADMIN_EMAILS as the project's established pattern. The agent used the same convention instead of inventing its own. Tiny detail; compounds over months."

Claude Opus 4.7 · dogfood session · 2026-04-22

STYLE-CONSISTENT PRS
Nobody else in agent-memory has first-class naming-convention tools. Mem0 / Zep / Letta don't model code-style at all.
06 / SPEED

The Negative Prover

Sub-50ms "nothing exists"

"'Does sanitizeHtml exist in this project?' — answered 'no' in 40ms with confidence 1.0. Grep on 400 files would have taken a full second and left the question ambiguous. The agent stopped hunting for ghosts."

Claude Opus 4.7 · dogfood session · 2026-04-22

< 50 MS DEFINITIVE NEGATIVES
RAG equates low similarity with uncertain — rarely says "no" confidently. Grep scales linearly with file count.
07 / SCOPING

The Tech Lead

ROI estimation via call-graph

"Before committing to a feature, the agent used Argos to map every file a change would touch — six, across three service boundaries. It flagged the effort as disproportionate and deferred the work. A human tech lead would have done the same scope check."

Claude Opus 4.7 · dogfood session · 2026-04-22

ACCURATE EFFORT ESTIMATES
No other code-memory engine surfaces call-graph structure for planning. Humans still do this by hand — the agent now gets the same answer for free.
NEW · v0.2
08 / MULTI-MODAL

The Multi-modal Librarian

Images, PDFs, audio — linked to code

"User shared a UI mockup. The LLM interpreted it — 'a 3-step Stripe checkout, Place Order button disabled until terms accepted' — and Argos stored that interpretation linked to checkoutHandler. Two weeks later, the 'why is the button disabled?' question resolved instantly."

1 CALL = IMAGE + CONTEXT + CODE LINK
Mem0 processes images server-side (cloud-only, paid). Zep / Letta are text-only. Argos is the first code-memory engine that handles multi-modal without shipping a vision stack of its own.
Services · The six most expensive problems we solve

Six services, ranked by how much they cost your team this quarter.

Each service is a working pipeline backed by deterministic structural retrieval — file:line citations, sub-millisecond P99, $0 per query, runs locally. Click in for the full pitch, the side-by-side math, and how to reproduce it on your repo. See all 14 services →

FLAGSHIP
#1 · SAST Noise →
Kill 70% of your SAST queue. Without replacing Snyk or Checkmarx.
CISO buyer · TAM $2-3B · 47k findings → 89 actually exploitable.
#2 · Compliance Audit Prep →
HIPAA · SOC 2 · PCI-DSS · FedRAMP · SOX 404. Audit prep in 5 minutes, not 5 weeks.
GRC / CISO buyer · TAM $5-10B · Complement to Drata / Vanta / SecureFrame.
#3 · Agent Token Burn →
Stop burning $1,350/month per autonomous agent on grep+read+summarize loops.
Dev / AI eng buyer · TAM $1-2B · ~150× token reduction, sub-millisecond, MCP-native.
SOON
#4 · M&A Due Diligence →
Deal-defining DD on a one-week clock. Tech debt, dead code, security posture for any acquisition.
PE fund / Big4 advisor · TAM $500M-1B · $25-50K per engagement, repeatable.
SOON
#5 · Refactoring Fear →
Know every caller before you rename anything. Find-all-callers + blast-radius proofs.
Senior dev / Tech lead · TAM $700M-1.5B · Local-first, deterministic, auditable.
SOON
#6 · New-Hire Onboarding →
From day-zero to first PR, in days. Code-tour + naming + architecture briefing in your IDE.
Eng manager / VP Eng · TAM $500M-1B · Cuts 6-month ramp to under 6 weeks.
Use cases · By role

Or pick the workflow that matches yours.

ArgosBrain ships one binary that adapts to where you work — security audits, MCP-compatible coding agents, enterprise compliance, e-commerce theming. Click your scenario for the opinionated install + tooling guide.

For AI agent builders →
Stop your autonomous agents burning $1,350/mo on codebase queries. ~150× token reduction, sub-millisecond, MCP-native. Drop-in for LangChain / OpenAI Agent SDK / Claude Agent SDK / custom.
For Security engineers →
Attack-surface mapping, dead-code reduction, living memory for Semgrep / CodeQL findings. We amplify your AppSec workflow — we don't replace it.
For MCP developers →
Drop-in MCP memory server. 7 tools. Rust core, stdio transport, zero-panic.
For Claude Code / Cursor users →
One install. Your agent remembers the repo across sessions. Works with any MCP-compatible CLI.
For Enterprise & Regulated →
Monolith migration, HIPAA / GDPR / PCI-DSS reachability proofs, M&A due diligence. Local, deterministic, air-gap friendly.
For Shopify agent builders →
Liquid + Dawn memory so your agent stops re-reading sections/*.liquid on every turn.
The problem

Your agent keeps forgetting.

Every session starts from scratch. Every query re-embeds files you've already seen. Every run rebuilds the repo map and throws it away.

The community has a name for this: context rot. Chroma's 2025 study measured it across 18 frontier models — every one degrades as input grows. Anthropic shipped a Memory Tool in September 2025, but it's a file primitive, not a brain.

Meanwhile, you're paying for the same file to be read 40 times a week. Cursor Ultra is $200/mo. Claude Max is $200/mo. Token bills don't lie.

$4B
Coding LLM
spend 2026
40×
Slower than
ArgosBrain
94%
Fewer tokens
with ArgosBrain
How it works

One brain. Every agent.

01 / INGEST

Ingest

Compiled Rust binary runs locally. Tree-sitter + SCIP parse your codebase into a unified graph. 28 languages. Updates instantly on file save.

02 / QUERY

Query

Any agent asks structural questions via standard MCP toolssymbol_exists, resolve_member, list_symbols, search. Sub-ms answers. Integrate it into your custom internal tools effortlessly.

03 / SAVE

Save

$0 per query, forever. No LLM in the retrieval loop. Local-first. Zero data egress. Toggle on/off, see the diff.

Live demo

Watch tokens burn.
Then stop.

Same repo. Same prompt. Same model (Claude Opus 4.7, temperature=0).
Left window: agent alone. Right window: agent + ArgosBrain.

Wall clock
23.4s VS 0.8ms
Cost
$2.18 VS $0.00
Tokens
48,200 VS 312
Why not something else

Built for code.
Nothing else comes close.

VS
General memory
Mem0 · Zep · Letta

LLM summarization destroys ASTs. We parse them.

$52M raised in the category — zero products built for code.

VS
Infinite context
Magic.dev · 100M windows

100M tokens still hallucinate symbols. And cost real money per call.

Our answers are ground truth, in 0.8 milliseconds.

VS
Cloud code engines
Augment · Cody

They ship your code to their servers and bill LLM cost per query.

We run local. $0 per query. Zero data egress.

VS
IDE-native
Cursor index · Copilot

Locked to one editor. We work in every MCP agent — including the ones above.

One brain, every tool.

The category, honestly

Broken down, one category at a time.

One giant table is unreadable. Here's the same information split into seven categories — ArgosBrain first, everyone else ranked against us. Click any competitor for the full page with citations.

01

Cost per retrieval query

ArgosBrain$0 — no LLM on read path
Zep / GraphitiFree retrieval (graph + semantic)
Mem0Embedding + vector search
MCP memory serverSubstring + full body
Aider~1 000 tokens / request
ContinuePrompt tokens (chunks injected)
Cursor · Windsurf · CopilotPrompt tokens every relevant query
CLAUDE.mdFull file in system prompt, every turn
Cline Memory BankFull MD bank at every session start
LettaLLM tool-call on every read
02

Code understanding depth

ArgosBrainSCIP + live LSP + tree-sitter, tiered per language
AiderTree-sitter surface names + PageRank
ContinueTree-sitter text chunks for embedding
CopilotSemantic repo indexing (opaque)
Cursor · WindsurfUndocumented
Cline · Mem0 · Zep · Letta · CLAUDE.md · MCP memoryNo code indexing — prose / text / JSON
03

Staleness / refactor safety

ArgosBrainFile-hash invalidation, automatic
Copilot28-day auto-expire + citation validation
AiderRecomputed per request (always fresh)
Zep / GraphitiBi-temporal edges (not code-aware)
ContinueOn re-index
Cursor · WindsurfUnknown
Cline · CLAUDE.mdManual edit only
Mem0 · Letta · MCP memoryNone
04

Local-only option

ArgosBrainYes, default — runs in-process
Windsurf · Zed · Cline · Aider · Continue · CLAUDE.md · MCP memoryYes
Mem0 · LettaOSS self-host yes; Cloud no
ZepCE deprecated Apr 2025 — Graphiti OSS only
Cursor · CopilotCloud-only
05

Published benchmark scores

ArgosBrainLongMemCode 99.2–100% across 16 corpora, P99 ≤ 0.82 ms
ZepDMR 94.8%, LongMemEval +18.5% / −90% latency
Mem0LoCoMo 91.6%, LongMemEval 93.4%
LettaTerminal-Bench #1 OSS (Letta Code)
All othersNone published
06

MCP + agent portability

ArgosBrainIs an MCP server — runs under every MCP client
MCP memory serverYes (reference implementation)
Continue · Cline · Mem0 · Zep · LettaMCP client only — can consume, not serve
CLAUDE.mdConvention, not a protocol
Cursor · Windsurf · Copilot · AiderNo — memory locked inside their tool
07

Openness

ArgosBrainBenchmark MIT, protocol open, engine commercial
Continue · Cline · Aider · Letta · GraphitiApache-2.0
Mem0 · MCP memoryMIT
ZepGraphiti OSS; Zep Cloud closed
Cursor · Windsurf · CopilotClosed source
We win / best in class Parity or partial match Weakest / we win by a wide margin
Best Weakest Neutral / tied Every cell traces to a source on the /vs/<competitor> page.
Two failure modes most memory systems miss

The 500K-token cliff

"State integrity degrades at 500K to 2M tokens. Roughly one-fifth to one-tenth the scale where retrieval architecture becomes critical." — Mark Hendrickson · Apr 2026

Long-context models don't solve memory. BEAM scores showed RAG degrading from 30.7% at 1M tokens to 24.9% at 10M, and contradiction resolution near zero at every tier. ArgosBrain's verify / dispute / zone transitions are exactly the write-integrity layer those numbers say is missing.

The graph phase transition

"Every practitioner has felt it. Your GraphRAG system is useless for weeks — hallucinating, missing obvious connections. Then suddenly, it works." — Alexander Shereshevsky · Graph Praxis

Flat vector RAG breaks on codebases because codebases are high-connectivity graphs (call sites, inheritance, imports). ArgosBrain is graph-first by design — petgraph + HNSW + keyword hybrid — which is why every cell in the "code-native" row above is red except ours.

Where we don't win — yet

The honest list.

"We win at everything" is a lie and engineers smell it instantly. Here's what we don't ship today.

IDE-native UX

Cursor and Copilot ship memory inside the editor with zero install. ArgosBrain runs as an MCP server you configure.

Managed cloud / team sync

Mem0 Cloud and Zep Cloud offer multi-user team memory out of the box. ArgosBrain is local-first; team sync is roadmap, not shipped.

General conversational memory

Mem0 holds 91.6% on LoCoMo. ArgosBrain targets ≥91.6% on LongMemEval — match, not beat. Our moat is code, not chat.

Free-text conceptual search

For pure-English queries like "rate limit fail open" — no symbol names, no identifiers — Grep is still the faster tool. Argos is for structural code questions; we'll point you at Grep when that's the right answer.

Live system state

Database rows, RLS policies, deploy logs, third-party API responses, runtime errors. Not our job. Use psql, provider CLIs, deploy hooks, browser devtools. We store code memory — not a proxy to production systems.

Vision / OCR / ASR ourselves

We don't ship a vision stack. Your agent's LLM interprets the file; we make sure that interpretation is remembered — linked to your codebase. One less binary, one less supply-chain surface, one less thing to audit.

Install

Free. No card. No catch.

Sign in with GitHub to get your free key. Your dashboard then shows a single copy-paste install line that includes your key — paste it in your terminal and you're done.

Sign in with GitHub — free
$ curl -fsSL https://argosbrain.com/install | sh && argosbrain init --key <your-free-key>

↑ This is what you'll paste in your terminal. Sign in to get the version with your free key embedded.

🔒 The Egress Promise
Your source code never leaves your machine. Retrieval, ingest, and the dashboard all run locally. No source, no file paths, no query content ever transmitted, on any tier. Air-gapped deployment available on Pro and Enterprise for regulated environments. Full data-handling details in /privacy.
macOS · Linux · Windows (WSL)
Single binary. No dependencies. Ships with a local dashboard at 127.0.0.1:3733 — open it with argosbrain dashboard.
Connects to Claude Code, Cursor, Codex CLI, and OpenCode automatically. Any MCP-compatible client works the same way.
Works with Claude Code Cursor Codex CLI OpenCode
Read the quick-start docs →
Pricing

Free is genuinely free.
Pay only when you outgrow it.

No 30-day trial clock. No credit card on the Free tier. Cancel any paid plan at any time — your subscription stays active through the end of the billing period and we offer a 14-day refund on your first paid charge.

Free
$0
No card · 1 active project
  • 1 active project at a time
  • All 32 ArgosBrain skills + every retrieval tool
  • Full sink scanning + reachability
  • Local dashboard (argosbrain dashboard)
  • Every MCP agent supported
Get started
Most popular
Pro
$19 / month
Unlimited projects · Cancel anytime
  • Unlimited active projects
  • Everything in Free, no caps
  • Custom sink packs
  • Preview release access
  • Email support < 48h
Start Pro
Enterprise
Contact us
Custom · Talk to sales
  • Everything in Pro
  • SSO (SAML / OIDC)
  • Audit logs
  • On-prem / air-gapped deployment
  • Dedicated support + SLA
Contact sales
Research

ArgosBrain: A Persistent, Code-Native Memory Layer for AI Coding Agents

Catalin Jibleanu et al. · April 2026 · Preprint
"Every AI coding agent in 2026 suffers from the same flaw: no persistent memory of the code it has seen. We present ArgosBrain, a Rust graph-memory engine that answers structural queries at sub-millisecond latency and $0 per query, on a new code-memory benchmark we authored (LongMemCode)."
Tweaks