Skip to content

README.md

Latest commit

 

History

History
140 lines (96 loc) · 4.92 KB

README.md

File metadata and controls

140 lines (96 loc) · 4.92 KB
Raw

HipCortex

PyPI npm License Release

AI coding agents forget decisions, re-read the same context, and burn tokens — HipCortex is local persistent memory you install once so Claude, Cursor, VS Code, and your Python/TS agents remember what matters and spend less on every turn.

⭐ If that solves a pain you feel, star the repo — it helps others find it.
💬 Tried it? Open an issue or leave a 👍/👎 comment — real feedback steers the next release.

Why it exists

Long agent sessions either dump full chat history into the prompt (expensive, noisy) or forget yesterday’s decisions (frustrating). HipCortex stores memories as a local causal graph, serves them over HTTP + MCP, and injects only the small, relevant slice your agent needs next.

You get Without HipCortex
Decisions persist across sessions “We already decided that” — lost
Smaller prompts (Headroom / Caveman modes) Context stuffing & higher API cost
One install for many hosts Hand-edited MCP configs per tool
Runs on your machine (Win / macOS / Linux) Cloud-only memory lock-in

Install in 60 seconds

Works on Windows, macOS, and Linux.

pip install -U hipcortex
hipcortex install          # pick your IDE (Claude, Cursor, VS Code, Grok, …)
hipcortex start            # local server on http://127.0.0.1:3030
hipcortex doctor           # health check

Non-interactive:

hipcortex install --yes
hipcortex install --url https://hipcortex.fly.dev   # optional managed endpoint

TypeScript client:

npm install hipcortex

VS Code / Antigravity VSIX (multi-OS server binaries bundled; extension 0.5.8):
Package from repo (vscode-extension) or latest GitHub Release VSIX. Display/description use v0.5.8 (not stale v0.5.0). Mac/Linux auto-chmod bundled bins.

code --install-extension hipcortex-memory-0.5.8.vsix

Honest support matrix (what’s native vs docs-only): docs/channels.md · CLI: hipcortex channels

60-second usage

Python

from hipcortex import HipCortexClient

client = HipCortexClient("http://127.0.0.1:3030")
client.add_memory(actor="alice", action="decided", target="Use Postgres for sessions")
print(client.search("sessions", limit=5))
# client.forget("alice")  # GDPR-style wipe for an actor

TypeScript

import { HipCortexClient } from "hipcortex";

const client = new HipCortexClient({ baseUrl: "http://127.0.0.1:3030" });
await client.addMemory({ actor: "alice", action: "decided", target: "Use Postgres" });
const { results } = await client.search({ query: "Postgres", limit: 5 });

Live try (no local install)

curl https://hipcortex.fly.dev/health

Where it plugs in

Surface How
Claude Code hipcortex install → skill + optional --mode proactive
Cursor / VS Code / Windsurf / Grok / … MCP config via wizard
Python agents pip install hipcortex + LangChain / CrewAI / AutoGen adapters
Node agents npm install hipcortex
Rust core Local webserver binary from Releases

Deep host notes: docs/hosts/README.md

What “good” looks like

  • Remember → agent stops re-asking the same project decisions
  • Recall → search / live beliefs return the right fact in one call
  • Lean context → fewer tokens than pasting full history
  • Yours → data stays local unless you point at a remote URL

Benchmark notes (local latency & token savings): BENCHMARK.md

Contribute & feedback

We ship faster when users tell us what broke or what you love.

  1. Star the repo if you want this to exist
  2. Install and run hipcortex doctor
  3. Report bugs / “I expected X” in Issues
  4. PRs welcome — docs/contributing.md

Docs & license

Doc For
docs/usage.md CLI, harness, day-to-day use
docs/architecture.md How the engine is built
docs/channels.md Channel honesty matrix
DEPLOY.md Self-host / Fly / Docker
DEVELOPMENT.md Build from source

License: Apache-2.0 · Version: product 0.5.2 · extension VSIX 0.5.8