Continuum
Continuum tackles the context amnesia problem in AI coding sessions by giving all your MCP clients a shared memory layer backed by SQLite and sqlite-vec. It exposes tools like `knowledge_create`, `knowledge_search`, and `knowledge_get` for storing and retrieving semantic lessons, plus `agent_dispatch` and `registry_list` for orchestrating isolated worktree sessions with collision detection. The setup seeds every project with a PLOT.md protocol that walks through Intake, Research, Verify, and Handoff phases. One client reads the plot and becomes the orchestrator, then hands off to fresh agents that can query what earlier sessions learned. The default embedder runs in-process with Transformers.js, or you can point it at Ollama or any OpenAI-shaped endpoint. Everything lives in one local SQLite file with no SaaS dependencies.
- GitHub stars
- 74
- tools
- 17
- transport
- HTTP
- env vars
- 4
- last updated
- May 13, 2026
Tools
17 toolsPublic tool metadata for what this MCP can expose to an agent.
project_listEnumerate registered projects
Enumerate registered projects
No parameter schema in public metadata yet.
project_getFetch one project
Fetch one project
No parameter schema in public metadata yet.
project_createRegister project, seed PLOT.md + knowledge
Register project, seed PLOT.md + knowledge
No parameter schema in public metadata yet.
project_renameRename a project
Rename a project
No parameter schema in public metadata yet.
project_deleteCascade delete (project + agents + lessons)
Cascade delete (project + agents + lessons)
No parameter schema in public metadata yet.
plotRead PLOT.md
Read PLOT.md
No parameter schema in public metadata yet.
plot_updateApply a unified git-format diff (zero fuzz, exact context match)
Apply a unified git-format diff (zero fuzz, exact context match)
No parameter schema in public metadata yet.
knowledge_listLesson metadata (slug, kind, agentSlug, timestamps). Optional kind filter. No content.
Lesson metadata (slug, kind, agentSlug, timestamps). Optional kind filter. No content.
No parameter schema in public metadata yet.
knowledge_searchSemantic query → ranked metadata. q free-text intent, optional kind, optional limit. No content.
Semantic query → ranked metadata. q free-text intent, optional kind, optional limit. No content.
No parameter schema in public metadata yet.
knowledge_getRead one lesson by slug — full body
Read one lesson by slug — full body
No parameter schema in public metadata yet.
knowledge_createRecord a new lesson — kind: 'fundamental' | 'situational'. Embedded automatically.
Record a new lesson — kind: 'fundamental' | 'situational'. Embedded automatically.
No parameter schema in public metadata yet.
knowledge_updateReplace lesson content. Re-embeds on save.
Replace lesson content. Re-embeds on save.
No parameter schema in public metadata yet.
knowledge_deleteRetire a lesson
Retire a lesson
No parameter schema in public metadata yet.
registry_listPaginated agent metadata — {data, page, limit, hasNextPage}. Optional status filter; default limit 10, max 50. No artifact bodies.
Paginated agent metadata — {data, page, limit, hasNextPage}. Optional status filter; default limit 10, max 50. No artifact bodies.
No parameter schema in public metadata yet.
agent_getFull record by slug — includes request, plan, implPrompt, coordinationBrief, postMergeNotes
Full record by slug — includes request, plan, implPrompt, coordinationBrief, postMergeNotes
No parameter schema in public metadata yet.
agent_createPersist a draft dispatch record
Persist a draft dispatch record
No parameter schema in public metadata yet.
agent_updateTransition status, edit fields
Transition status, edit fields
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
ORCHESTRATOR_DB_PATHdefault: /data/orchestrator.dbSQLite path inside container
EMBEDDER_URLOptional HTTP embedder (Ollama/TEI/OpenAI-compatible). Unset = in-process embedder.
EMBEDDER_MODELdefault: Snowflake/snowflake-arctic-embed-m-v1.5Embedding model id
EMBEDDER_DIMdefault: 768Embedding vector dimension
Readme
Shared memory + orchestration for your coding agents.
One MCP server. Tell any client to read the plot — it becomes the orchestrator.
Dispatches fresh agents in isolated worktrees, shares lessons across every Claude Code / Codex / Cline chat on the project.
Details
- Repository
- github.com/pouyahasanamreji/continuum
- Website
- github.com/pouyahasanamreji/continuum
- Category
- AI & LLM Tools
- Package
docker.io/pouyahasanamreji/continuum:0.3.0- Transport
- HTTP
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Lumenahmedeid1/lumenSelf-hostable agentic-AI LMS: catalog, RAG tutor, FSRS reviews, AI authoring, ingest.69stars
DOMShellapireno/domshellDrive Chrome with filesystem commands (ls, cd, grep, click, type). One MCP tool, multi-agent.59stars
MCP AutoMemverygoodplugins/mcp-automemGraph-vector memory for AI assistants using FalkorDB and Qdrant51stars
Engramtstockham96/engramIntelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.39stars
Local FAISS MCP Servernonatofabio/local_faiss_mcpLocal FAISS vector database for RAG with document ingestion, semantic search, and MCP prompts.30stars
SAME - Stateless Agent Memory Enginesgx-labs/statelessagentPersistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.19stars