Core

Persistent memory for AI coding agents.

Connector by omega-memory · GitHub account verified by the MCP Registry

IndexedApache-2.0Local (stdio)★ 224

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/omega-memory-core

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Persistent memory for AI coding agents. #1 on LongMemEval. Local-first.

Use cases: agent-memory

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 7 read · 5 write · 1 delete · 6 not yet classified
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Tools by what they do 19

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

omega_profile
omega_protocol
omega_query
omega_reflect
omega_review
omega_stats
omega_tools

Write 5 · Create, change, send or run things.

context_packet
omega_call
omega_checkpoint
omega_remind
omega_store

Delete 1 · Delete, drop, revoke or wipe things.

omega_memory

Not yet classified 6 · We could not tell from the name and description.

context_assemble
omega_consult_claude
omega_consult_gpt
omega_maintain
omega_resume_task
omega_welcome

Files it touches

Any path the agent passes to its tools

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

context_assemble
Assemble OMEGA's active context as structured sections plus a pre-rendered markdown blob. Harness-agnostic; clients splice into their own system prompt. For Claude Code, omega_welcome remains the richer briefing surface.
context_packet
Build a compact task-aware memory packet for the current work. Combines retrieval seeds, graph chains, safety filtering, warning receipts, and token-budgeted markdown.
omega_call
Execute any OMEGA tool by name. Use omega_tools() first to discover available tools and their parameters. Example: omega_call(tool='omega_query', args={'query': 'auth decisions', 'mode': 'semantic'})
omega_checkpoint
Save a task checkpoint: captures current plan, progress, files touched, decisions, and key context. Enables seamless session continuity.
omega_consult_claude
Consult Claude for a second opinion on hard problems (for non-Anthropic agents). Use when stuck (10+ min or 3+ failed approaches), facing irreversible architecture decisions, debugging dead ends, cross-validating fragile solutions, or bridging domain expertise gaps. Do NOT use for simple tasks, speed-sensitive work, or when tests already pass.
omega_consult_gpt
Consult GPT for a second opinion on hard problems. Use when stuck (10+ min or 3+ failed approaches), facing irreversible architecture decisions, debugging dead ends, cross-validating fragile solutions, or bridging domain expertise gaps. Do NOT use for simple tasks, speed-sensitive work, or when tests already pass.
omega_maintain
System housekeeping and constraint management. Use 'health' to check database size and integrity, 'consolidate' to prune stale memories, 'compact' to merge near-duplicates, 'discover_connections' to actively find and link related memories (generates cross-type insights), 'backup'/'restore' for data safety, 'clear_session' to purge a session's data, 'synthesize_insights' to generate system insights, 'backfill_embeddings' to fill missing vectors, 'job_status' to poll a previously submitted async job, 'list_constraints'/'check_constraint'/'save_constraints' to manage file constraint rules. Long-r…
omega_memory
Manage a specific memory by ID: edit its content, delete it, mark it as superseded, mark it as helpful/unhelpful/outdated, find similar memories, traverse relationship edges, link two memories, or list flagged memories for review. Use when acting on an individual memory rather than searching broadly.
omega_profile
Read or update the user's persistent profile (name, preferences, working style) or list all stored preferences. The profile persists across sessions and informs agent behavior. Default action is 'read'.
omega_protocol
Retrieve your operating rules and behavioral guidelines for this session. Returns context-sensitive instructions covering memory usage, coordination, reminders, and workflow. In multi-agent mode, includes a session role (primary/challenger/verifier) for behavioral diversity. Call after omega_welcome at session start, or on-demand for a specific section.
omega_query
Search memories. Modes: 'semantic' (default) for meaning-based search, 'phrase' for exact substring match, 'timeline' for recent memories grouped by day, 'browse' for listing by type/session/recent.
omega_reflect
Analyze memory quality and knowledge evolution. 'contradictions' finds conflicting memories on a topic, 'evolution' traces how understanding changed over time, 'stale' surfaces old never-accessed memories for review.
omega_remind
Manage time-based reminders: set new reminders, list active ones, or dismiss by ID.
omega_resume_task
Resume a previously checkpointed task. Retrieves the latest checkpoint with full plan, progress, files, decisions, and next steps.
omega_review
Review a code diff with multi-agent specialist panel. Uses OMEGA memory for codebase context, team conventions, and past incident awareness. Returns findings sorted by severity with confidence scores.

Show 4 more tools

omega_stats
View analytics and behavioral insights: memory breakdown by type, per-session statistics, weekly digest, forgetting audit log, deduplication stats, access rate trends, milestones, unified diagnostic report, tool utilization monitoring, and behavioral patterns (habits_list, habits_analyze, habits_profile, habits_confirm, habits_deny, habits_recommendations).
omega_store
Store a memory with optional type and metadata. Use when the user says 'remember this' or for programmatic capture (decisions, lessons, errors). Defaults to type 'memory' if event_type is omitted.
omega_tools
List available OMEGA tools or get the full schema for a specific tool. Call with no args to see all tool names and descriptions. Call with tool='name' to get its full input schema so you know what arguments to pass to omega_call.
omega_welcome
Session startup briefing. Call at the beginning of every session to load recent context, active reminders, and user profile. Returns what the agent needs to continue where the last session left off.

Compare and alternatives

Featured in

Signals

Stars: 224
Forks: 32
Open issues: 2
Contributors: 10
Weekly downloads: 1,911
Last commit: Oct 9, 2026 (19 days ago)
Last release: Oct 8, 2026 (20 days ago)
Last package publish: Oct 8, 2026 (20 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.omega-memory/core
Version: 0.9.3
Auth: No auth
Packages: pypi omega-memory
License: Apache-2.0
Repository: github.com/omega-memory/core
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql