Skip to content

docs(readme): expand 'How It Compares' with letta + LangMem + decision rules #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yakuphanycl merged 1 commit into from
Apr 27, 2026
Merged

docs(readme): expand 'How It Compares' with letta + LangMem + decision rules #40

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 12 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,17 +112,24 @@ instinct serve --transport streamable-http # streamable HTTP
instinct serve --port 3777
```

## Why Not Just CLAUDE.md?
## How It Compares

CLAUDE.md is good for hand-written rules. instinct is for patterns that should
earn their way into rules through repetition.

| Surface | Best fit | Different because |
|---|---|---|
| `instinct` | Coding-agent pattern memory | Local SQLite, confidence tiers, decay, cross-project promotion, MCP tools. |
| [Mem0](https://github.com/mem0ai/mem0) | General AI memory layer | Broader memory product; instinct is narrower and coding-agent focused. |
| [claude-mem](https://github.com/search?q=claude-mem&type=repositories) | Claude-specific memory experiments | instinct exposes MCP tools plus CLI exports across multiple agents. |
| [Pieces](https://pieces.app/) | Developer snippets and workflow context | instinct stores repeated behavioral patterns rather than a general knowledge library. |
| `instinct` | Coding-agent pattern memory | Local SQLite, confidence tiers, decay, cross-project promotion, MCP-native — works with any MCP-compatible agent. |
| [Mem0](https://github.com/mem0ai/mem0) | General LLM memory layer | Broader memory product (chat history, episodic facts); instinct is narrower and coding-agent focused on behavioral patterns. |
| [Letta](https://github.com/letta-ai/letta) (formerly MemGPT) | Stateful agent runtime | Full agent framework with memory built-in; instinct is a memory-only sidecar you bolt onto your existing agent. |
| [LangMem](https://github.com/langchain-ai/langmem) | Memory for LangChain | Tied to LangChain ecosystem; instinct is framework-agnostic via MCP. |
| [claude-mem](https://github.com/search?q=claude-mem&type=repositories) | Claude-specific memory experiments | instinct exposes MCP tools plus CLI exports across Claude, Cursor, Windsurf, Goose, and Codex. |
| [Pieces](https://pieces.app/) | Developer snippets and workflow context | instinct stores repeated behavioral patterns; Pieces stores artifacts (snippets, links, screenshots). |
| `CLAUDE.md` / `.cursorrules` | Hand-written rule files | Flat text, manual maintenance. instinct can export to these formats once a pattern matures. |

**When to reach for instinct:** your agent makes the same correction or follows the same workflow more than 3 times and you don't want to keep retyping. instinct records once, promotes after repetition, and surfaces it back automatically.

**When to reach for the others:** chat-history recall (Mem0), full agent runtime with built-in memory (Letta), LangChain integration (LangMem), or static hand-curated rules (CLAUDE.md / .cursorrules).

## Storage and Runtime

Expand Down
Loading