@nano-step/nano-brain 2026.6.401 → 2026.6.403
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +49 -0
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -10,6 +10,55 @@
|
|
|
10
10
|
|
|
11
11
|
nano-brain is a persistent memory server for AI coding agents that solves session amnesia. It automatically ingests AI sessions, notes, and codebase files, indexes everything with hybrid search (BM25 + pgvector), and serves memories via MCP tools and REST API. Built in Go with PostgreSQL — single static binary, zero CGO dependencies.
|
|
12
12
|
|
|
13
|
+
## Use Cases
|
|
14
|
+
|
|
15
|
+
### Multi-machine developer (primary use case)
|
|
16
|
+
You work on your office PC, home machine, and personal laptop — each with a different Claude Code or OpenCode session. Without shared memory, your AI agent forgets everything between machines.
|
|
17
|
+
|
|
18
|
+
Deploy nano-brain on a VPS (or any always-on server) with a PostgreSQL instance. Every session you run on any machine gets harvested and indexed there. When you switch machines, your agent picks up exactly where you left off — decisions, context, code knowledge, all there.
|
|
19
|
+
|
|
20
|
+
```
|
|
21
|
+
Office PC ──┐
|
|
22
|
+
├──► nano-brain on VPS ──► shared PostgreSQL
|
|
23
|
+
Home Mac ───┘
|
|
24
|
+
```
|
|
25
|
+
|
|
26
|
+
### Persistent AI agent memory
|
|
27
|
+
AI agents forget everything when the session ends. nano-brain gives them durable, searchable memory across sessions — decisions made, patterns discovered, code written — so they don't repeat work or ask the same questions twice.
|
|
28
|
+
|
|
29
|
+
### Code intelligence for large codebases
|
|
30
|
+
nano-brain builds a symbol graph of your codebase: functions, types, dependencies, call chains. Agents can ask "what breaks if I change this function?" (`memory_impact`) or "trace the call chain from this entry point" (`memory_trace`) — across files, across sessions.
|
|
31
|
+
|
|
32
|
+
### Notes and documentation search
|
|
33
|
+
Write structured notes, ADRs, or decision records into nano-brain. Hybrid search (BM25 + semantic) retrieves them by keyword or concept. Agents can surface the right context without you having to remember where you put it.
|
|
34
|
+
|
|
35
|
+
### Team knowledge base (no per-member setup)
|
|
36
|
+
Deploy one nano-brain server for the whole team. Every developer's AI agent connects to the same PostgreSQL instance — decisions, architecture notes, code intelligence, and session learnings are instantly shared across the team. New team members get full project context from day one without any setup on their machine.
|
|
37
|
+
|
|
38
|
+
```
|
|
39
|
+
Dev A (office) ──┐
|
|
40
|
+
Dev B (remote) ──┼──► nano-brain on team server ──► shared PostgreSQL
|
|
41
|
+
Dev C (new hire) ──┘
|
|
42
|
+
```
|
|
43
|
+
|
|
44
|
+
Role-based access: admins get full read/write, developers get read/write scoped to their workspace, stakeholders or reviewers get read-only access.
|
|
45
|
+
|
|
46
|
+
### Knowledge preservation when an engineer leaves
|
|
47
|
+
A senior engineer resigns. Without nano-brain, their institutional knowledge — why certain decisions were made, which parts of the codebase are fragile, what was tried and failed — walks out the door with them.
|
|
48
|
+
|
|
49
|
+
With nano-brain, their sessions are already harvested and indexed. The team can still ask "why did we pick this approach?" or "what did Alice know about the payment service?" and get answers from her past sessions.
|
|
50
|
+
|
|
51
|
+
### Freelancer / consultant context switching
|
|
52
|
+
You work on 3 client projects in parallel. Each is a separate workspace. When you switch clients, run `nano-brain wake-up` to get an instant briefing — recent work, active collections, key context — and your AI agent picks up exactly where you left off without re-reading the codebase.
|
|
53
|
+
|
|
54
|
+
### Legacy codebase archaeology
|
|
55
|
+
You inherit a 5-year-old codebase with minimal documentation and no original authors to ask. Index it into nano-brain. Your AI agent can now answer "what does this function do?", "why does this class exist?", and "if I change this file, what else breaks?" — navigating cross-file relationships without reading 200k lines manually.
|
|
56
|
+
|
|
57
|
+
Go, TypeScript, Python, JavaScript supported today. Rust, Java, and others planned.
|
|
58
|
+
|
|
59
|
+
### Pre-commit / pre-PR impact check
|
|
60
|
+
Before pushing, run `memory_impact` on your changed files to discover what else in the codebase depends on them — across files, across repos in the same workspace. Catch breaking changes before they hit CI. *(Multi-file diff-aware mode in roadmap.)*
|
|
61
|
+
|
|
13
62
|
## Key Features
|
|
14
63
|
|
|
15
64
|
- **Hybrid search** — BM25 full-text + pgvector HNSW cosine similarity + RRF fusion + recency decay
|