Kortexio/ContextMemory
Agentic gateway providing persistent LLM memory via a markdown wiki. Open-source core of Kortexio. - Kortexio/ContextMemory
7 stars · 1 forks
README
Try it (3 commands) · Engines · Docs · vs Mem0 / Zep / Letta
Self-hosted memory gateway for your llama.cpp / vLLM server.
Put one OpenAI-compatible /v1 URL in front of your engine. Your client sends only the new message; the gateway keeps session memory as markdown you can open, edit, and diff. No vector DB, no client rewrite.
Try it in three commands git clone https://github.com/Kortexio/ContextMemory.git && cd ContextMemory docker compose -f docker-compose.yml -f docker-compose.llamacpp.yml up --build -d # CPU; GPU: docker-compose.vllm.yml ./scripts/aha-chat.sh # Windows: .\scripts\aha-chat.ps1 aha-chat sends two requests in the same session. The second one carries only the new question: ==> Turn 1: "Remember this for later: our staging database host is postgres-staging-01." ==> Turn 2: "What is our staging database host?" (no history in the request body) AHA OK — the client sent no history; the gateway remembered 'postgres-staging-01'.
The same check runs in CI against a real llama-server on every push (e2e-llamacpp). First start downloads a ~2 GB GGUF; pick another model with LLAMACPP_HF_MODEL (Engines). Admin UI: http://localhost:5200.
What is ContextMemory? ContextMemory is the open-source agentic memory gateway behind Kortexio. Your app (or Cursor/Claude) keeps talking to a normal chat API. The gateway:
Authenticates the tenant and attaches session wiki + history Runs an agentic tool loop when tools are enabled (wiki search, sandbox, MCP, …) Applies skills, guardrails, validators, and optional HITL before destructive actions Returns a standard OpenAI-shaped chat.completions response (streaming supported)
Your client (OpenAI SDK / Cursor MCP / curl) │ ▼ POST /v1/chat/completions ┌────────────────────────────────────────────┐ │ ContextMemory (.NET 9) │ │ Auth · session wiki · Global Wiki tool │ │ Agentic loop · skills · guardrails · HITL │ │ LLM backend (per app — BYO engine) │ └───────┬──────────────────┬─────────────────┘ ▼ ▼ sandbox-runtime mcp-runtime / MCP servers (shell/python/node) (HTTP + stdio, OAuth) or Azure ACA sessions
Honest boundaries: this is a gateway + server-side harness, not a client agent framework (LangGraph/CrewAI) and not an agent OS (Letta). You keep your OpenAI client; the loop runs on the server. LLM engines: ContextMemory does not ship or lock to one inference stack. Per tenant you pick any OpenAI-compatible /v1 host — Ollama, vLLM, LM Studio, ExLlamaSharp, OpenAI, Azure-compatible, LiteLLM, custom. Compose ships llama.cpp and vLLM overrides; swap engines per app in Admin → Config → LLM. How we compare (Mem0 / Zep / Letta / why we are not RAG): docs/compare.md.
What it gives developers
You need… ContextMemory provides…
Memory that survives turns without rewriting your client Session markdown wiki + history inject; send only the new message
Memory you can open, edit, audit Files on disk / Postgres — not opaque embeddings
Shared company/docs knowledge in chat Global Wiki digests + on-demand wiki_search / wiki_grep (not classic RAG / embeddings)
Tools without a second orchestrator Same /v1: sandbox + MCP + wiki tools
Safer agents Skills & guardrail packs, validators, HITL [CONFIRM:id]
Cursor / Claude permanent memory fast MCP wedge: memory_save / memory_search / memory_get
Any LLM per tenant BYO /v1 — Ollama, vLLM, LM Studio, ExLlamaSharp, OpenAI, Azure-compatible, custom
Operate without a test client Admin + Playground
Full control / zero ops Docker self-host · Kortexio Cloud (cmk_live_…)
Capabilities (summary) Full detail: docs/architecture-and-features.md · Admin: docs/admin-ui.md · HITL: docs/hitl.md.
Area Highlights
Memory Session wiki + rolling summary; history budgets; Global Wiki digests/FTS/revisions (asOf); no vector RAG
Agentic Server-side tool loop; sandbox; MCP catalog; artifacts; subagents; validators; HITL; egress policy
Skills Platform + per-app skills/guardrails (skill / always_on / requestable)
MCP Outbound wedge (Cursor → CM) · inbound catalog (CM → your MCP servers)
Ops Admin UI · File or Postgres · Prometheus /metrics · Compose (API + Admin + mcp-runtime + sandbox)
More ways to run The gateway talks OpenAI-compatible /v1 to the engine (and Ollama native /api/chat when you need num_ctx). Change the engine anytime in Admin → Config → LLM or PATCH /admin/apps/{id}/config. Engine already running (llama-server, vLLM, LM Studio, …) — API image only docker run --rm -p 5100:8080 \ -v contextmemory-data:/app/data \ -e ContextMemory__MasterKey=cm_master_dev_key_change_me \ -e ContextMemory__Apps__demo-dev__ApiKey=cm_live_dev_key_change_me \ -e ContextMemory__Apps__demo-dev__LlmBackend=openai-compatible \ -e ContextMemory__Apps__demo-dev__LlmModel=local-model \ -e ContextMemory__Apps__demo-dev__LlmEndpoint=http://host.docker.internal:8080 \ --add-host=host.docker.internal:host-gateway \ ghcr.io/kortexio/contextmemory:latest Host-level default for all apps: ContextMemory__LlmEndpoint. Ollama on the host works too (ContextMemory__LlmEndpoint=http://host.docker.internal:11434). Engine flags that matter (llama.cpp --jinja, vLLM tool parser): Engines. Full stack (API + Admin + MCP + sandbox): docs/self-host.md. Cursor / Claude memory (MCP) git clone https://github.com/Kortexio/ContextMemory.git cd ContextMemory/mcp-server && npm install && node print-mcp-config.mjs Paste into Cursor → Settings → MCP (or ~/.cursor/mcp.json). Same snippet works for Claude Desktop. Details: mcp-server/README.md. Then, in two separate chats:
Chat You say Agent should
A Remember: staging DB is postgres-staging-01 memory_save
B (new) What is our staging DB? memory_search + answer
Same flow without Cursor (wiki API, no LLM): ./scripts/aha-demo.sh or .\scripts\aha-demo.ps1. No GPU, no ops: Kortexio Cloud
Kortexio Cloud Self-host (this repo)
Best for Zero ops Full control (API + Admin + MCP + sandbox)
Key cmk_live_… (no X-App-Id) cm_live_… + X-App-Id
Chat body Identical OpenAI /v1 Identical OpenAI /v1
LLM BYO provider in dashboard BYO engine in Admin / env
Guides: Cloud · Self-host Chat drop-in curl -X POST http://localhost:5100/v1/chat/completions \ -H "Content-Type: application/json" \ -H "X-App-Id: demo-dev" -H "X-User-Id: user-42" -H "X-Session-Id: sess-abc" \ -H "Authorization: Bearer cm_live_dev_key_change_me" \ -d '{"model":"local-model","messages":[{"role":"user","content":"Hello"}]}' Thin header helpers (not full SDKs): @kortexio/contextmemory · kortexio-contextmemory
Documentation & support
Doc Topic
docs/compare.md Why it exists · vs Mem0 / Zep / Letta · why we are not RAG
docs/architecture-and-features.md Wiki, temporal facts, agentic, skills, LLM backends
docs/admin-ui.md Admin UI map
docs/hitl.md Human-in-the-loop
docs/api.md HTTP API
docs/cloud.md · docs/self-host.md Cloud · Docker / Compose
docs/ops.md Ops & troubleshooting
docs/README.md Full docs index
Website: kortexio.io · Email: hello@kortexio.io
License AGPL-3.0 for this open-source core — self-host it freely, including commercially. Need to embed it in a closed-source product without AGPL obligations? Use Kortexio Cloud or a commercial license. See docs/license-and-support.md.