Helios
Helios is a token-budgeted, drift-aware MCP memory server for AI coding agents across IDEs, CLIs, and hosts. You can:
Store, recall, supersede, revalidate, deprecate, and audit atomic project memories with FTS5 search and global rules.
Anchor memories to repo files so Git webhooks flag changed facts as [STALE], then update or revalidate them.
Inspect memory history/lineage, prune stale or expired records, and manage scope aliases or renames.
Change runtime settings live, including word limits, TTLs, and Git webhook config, without restarting.
Generate client setup configs/directives for Cursor, Claude, VS Code, Codex, Windsurf, OpenCode, and others; switch roles or uninstall cleanly.
Manage remote Git webhooks and export Markdown mirrors or crash-safe portable backup bundles.
Serve MCP over HTTP/SSE plus setup, health, and export HTTP routes.
Receives git push webhooks so that memories anchored to repo config files are automatically flagged as [STALE]; also supports listing/enabling repo webhooks conversationally via the manage_git_webhooks tool.
Receives git push webhooks so that memories anchored to repo config files are automatically flagged as [STALE]; also supports listing/enabling repo webhooks conversationally via the manage_git_webhooks tool.
Receives git push webhooks so that memories anchored to repo config files (e.g. docker-compose.yml, prisma/schema.prisma) are automatically flagged as [STALE]; also supports managing repo webhooks via the manage_git_webhooks tool using a GitHub PAT.
Receives git push webhooks so that memories anchored to repo config files are automatically flagged as [STALE]; also supports listing/enabling repo webhooks conversationally via the manage_git_webhooks tool.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Helios save that the staging API runs on port 8080 behind Caddy"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
☀️ Helios
A token-budgeted, drift-aware MCP memory engine for AI coding agents.
Built for personal use across homelab services and multiple workstations. Open-sourced if you find it helpful.
Why Helios? • Quick Start • 1-Liner Client Setup • How Drift Detection Works • Architecture • MCP Tools
I built Helios because I was tired of my AI coding agents bloating their context windows with repetitive prompt files and trusting outdated architecture configs after someone pushed code. It runs quietly in my homelab across laptops, headless CLI boxes, and different IDEs—and here it is if you want to use it.
💡 Why Helios?
AI coding agents usually suffer from two major pain points: amnesia (forgetting ports, conventions, and architecture choices between sessions) and knowledge drift (relying on stale documentation or outdated configs). Most memory tools either inject giant text dumps into every turn or rely on heavy vector databases that don't know when a git push invalidated a fact.
Helios solves this with a lightweight, token-budgeted approach:
Approach | Token Overhead | Handles Contradictions? | Detects Code/Config Drift? | Cross-IDE / Multi-Host? |
Static | High (loaded every turn) | ❌ Manual edits only | ❌ Silently goes stale | ❌ Per-machine / per-repo |
Vector / RAG Memory Servers | High (dumps long chunks) | ❌ Keeps old & new facts | ❌ Blind to | ⚠️ Usually cloud-locked |
☀️ Helios | Ultra-Low (≤ 25 words/fact) | ✅ Deterministic slot supersession | ✅ Git webhooks flag | ✅ Shared across IDE, CLI & SSH |
Core Design Pillars
Strict Token Diet: Enforces atomic, high-density facts (
≤ 25 wordsby default) so agent context windows stay lean, fast, and focused.Write-Through Architecture (Definition of Done): Replaces fragile deferred end-of-session memory saves with continuous, atomic persistence. Tasks altering infrastructure, ports, schemas, dependencies, or resolving non-obvious bugs are strictly incomplete until recorded in Helios.
Deterministic Lineage (AUDN Protocol): Facts operate on Add, Update, Deprecate, or No-op semantics. Saving a fact to an existing
(scope, subject)slot automatically supersedes the old fact and logs the transition in a historical audit trail.Git-Anchored Drift Detection: Memories can be anchored to repo configuration files (e.g.,
docker-compose.yml,prisma/schema.prisma). When agit pushmodifies an anchored file on GitHub, Forgejo, Gitea, or GitLab, Helios automatically flags the memory as[STALE]so your agent inspects the diff before acting.Dual-Plane Storage: Sub-millisecond SQLite WAL + FTS5 (BM25) full-text search for agents, mirrored into human-readable Markdown files (
/data/exports/<scope>.md) and crash-safe.tar.gzonline snapshots for developers.Live Day-2 Control Plane: Change word limits, episodic TTLs, scope aliases, and Git webhooks conversationally from your IDE without restarting containers.
Related MCP server: Thoth-Mem
🚀 1. Quick Start: Server Deployment
Create a compose.yaml file (or paste directly into Dockhand / Portainer) and run docker compose up -d:
compose.yaml
services:
helios:
image: ghcr.io/brazaoo4/helios:latest
# Or to build locally from source:
# build: .
container_name: helios
restart: unless-stopped
user: "1000:1000" # Must match ownership of your host data directory
ports:
- "8000:8000" # Omit if routing internally via a reverse proxy network
volumes:
# [MANDATORY] Persistent storage for SQLite WAL (memory.db) & Markdown exports
- ./data:/data
environment:
# ========================================================================
# 1. MANDATORY / CORE SETTINGS
# ========================================================================
- TZ=UTC
- MEMORY_DATA_DIR=/data
# ========================================================================
# 2. RECOMMENDED SECURITY (Required if exposed outside a private LAN/VPN)
# ========================================================================
# Shared Bearer / ?token= key required for /mcp, /sse, and /export/*.
# Leave empty ONLY if running on a trusted local network or Tailscale mesh.
- HELIOS_API_KEY=
# Shared HMAC-SHA256 secret for verifying POST /webhook/git payloads.
# Generate with: openssl rand -hex 32
- HELIOS_WEBHOOK_SECRET=
- HELIOS_REQUIRE_WEBHOOK_SECRET=false
# ========================================================================
# 3. OPTIONAL: REVERSE PROXY & ENGINE TUNABLES (Also live-editable via MCP)
# ========================================================================
# Override base URL used in /setup scripts (auto-detected from proxy headers if empty)
- HELIOS_PUBLIC_URL=
- HELIOS_ALLOWED_ORIGINS=*
- HELIOS_WORD_LIMIT=25
- HELIOS_EPISODIC_TTL_DAYS=14
- HELIOS_CHANGELOG_LIMIT=100
# ========================================================================
# 4. OPTIONAL: CONVERSATIONAL GIT WEBHOOK MANAGER (manage_git_webhooks)
# ========================================================================
# Only needed if you want your AI agent to list/enable repo webhooks via chat.
# Leave empty if you prefer adding webhooks manually in your Git UI.
- HELIOS_GIT_PROVIDER= # forgejo | gitea | github | gitlab
- HELIOS_GIT_API_URL= # e.g., https://git.example.com or https://api.github.com
- HELIOS_GIT_TOKEN= # PAT with repo/webhook permissions
- HELIOS_GIT_OWNER= # Optional username/org filter
- HELIOS_WEBHOOK_URL= # e.g., https://helios.example.com/webhook/git
healthcheck:
test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8000/health"]
interval: 30s
timeout: 5s
retries: 3Pre-Flight Host Notes
Volume Permissions (
1000:1000): Helios runs rootless asuid=1000(gid=1000). Ensure your host bind-mount directory is owned by1000:1000before starting:mkdir -p ./data && chown -R 1000:1000 ./dataReverse Proxy (Nginx Proxy Manager / Caddy / Traefik): If exposing Helios over HTTPS, disable proxy buffering on your reverse proxy so SSE streams (
/sseand/mcp) flush immediately:proxy_buffering off; proxy_cache off; proxy_read_timeout 86400s;Cold-Boot Seeding (Optional): If you drop a
seed.yamlfile (see seed.example.yaml) into./data/seed.yaml, Helios will automatically ingest it on startup and rename it toseed.yaml.imported.
If you aren't pulling a pre-built image and want to build from the repository:
git clone https://github.com/brazaoo4/helios.git
cd helios
cp .env.example .env
mkdir -p data && chown -R 1000:1000 data
docker compose up -d --build⚡ 2. Client Installation for AI Agents
Helios supports zero-friction onboarding across Antigravity, Cursor, Claude Desktop, Claude Code, OpenAI Codex, Windsurf, VS Code (GitHub Copilot), and OpenCode on Linux, macOS, and Windows.
2.1 Conversational AI Setup (1 Prompt)
Paste this single prompt into your coding agent (Claude Code, Cursor, Antigravity, Codex, Windsurf, VS Code, OpenCode):
Fetch https://<your-helios-host>/setup and configure my local MCP client, global directives, and /remember skill.The agent fetches GET /setup, detects your OS and IDE, safely merges the "helios" server entry into your MCP configuration without overwriting existing servers, adds the Helios directive block, and installs the /remember skill.
2.2 Instant Terminal 1-Liner Setup
Or run the automated onboarding script directly in your terminal:
Linux / macOS (Bash):
curl -fsSL https://<your-helios-host>/setup.sh | bashHeadless server CLI role (adds strict log-truncation rules like --tail=50):
curl -fsSL "https://<your-helios-host>/setup.sh?role=server-cli" | bashWindows (PowerShell):
irm https://<your-helios-host>/setup.ps1 | iexHeadless server CLI role:
irm "https://<your-helios-host>/setup.ps1?role=server-cli" | iexMulti-Client Auto-Detection & Token Passing:
The setup scripts automatically detect and configure Antigravity (mcp_config.json + GEMINI.md + /remember), Cursor (~/.cursor/mcp.json + rules/helios.mdc), Claude Desktop (claude_desktop_config.json), Claude Code (claude mcp add + ~/.claude/CLAUDE.md), OpenAI Codex (~/.codex/config.toml + ~/.codex/AGENTS.md), Windsurf (~/.codeium/windsurf/mcp_config.json + memories/global_rules.md), VS Code (User/mcp.json + ~/.github/copilot-instructions.md), and OpenCode (~/.config/opencode/opencode.json + AGENTS.md).
If HELIOS_API_KEY is enabled, append ?token=<your_key> to the setup URL.
Client Configuration Paths & Snippets
Antigravity CLI / IDE (
~/.gemini/config/mcp_config.json|%USERPROFILE%\.gemini\config\mcp_config.json):{ "mcpServers": { "helios": { "url": "https://<your-helios-host>/mcp" } } }Cursor IDE (
~/.cursor/mcp.json|%USERPROFILE%\.cursor\mcp.json):{ "mcpServers": { "helios": { "url": "https://<your-helios-host>/sse" } } }Claude Desktop (
claude_desktop_config.jsonin~/.config/Claude/~/Library/Application Support/Claude/%APPDATA%\Claude):{ "mcpServers": { "helios": { "command": "npx", "args": ["-y", "mcp-remote", "https://<your-helios-host>/sse"] } } }Claude Code CLI:
claude mcp add --transport sse helios https://<your-helios-host>/sseOpenAI Codex CLI (
~/.codex/config.toml|%USERPROFILE%\.codex\config.toml):[mcp_servers.helios] url = "https://<your-helios-host>/mcp"Windsurf IDE (
~/.codeium/windsurf/mcp_config.json|%USERPROFILE%\.codeium\windsurf\mcp_config.json):{ "mcpServers": { "helios": { "serverUrl": "https://<your-helios-host>/mcp" } } }VS Code / GitHub Copilot (
~/.config/Code/User/mcp.json|~/Library/Application Support/Code/User/mcp.json|%APPDATA%\Code\User\mcp.json):{ "servers": { "helios": { "type": "http", "url": "https://<your-helios-host>/mcp" } } }OpenCode CLI (
~/.config/opencode/opencode.json|%USERPROFILE%\.config\opencode\opencode.json):{ "$schema": "https://opencode.ai/config.json", "mcp": { "helios": { "type": "remote", "url": "https://<your-helios-host>/mcp", "enabled": true } } }
2.3 Safe In-Place Directive Management (<!-- HELIOS:START -->)
Helios encloses its global agent instructions inside idempotent HTML comment delimiters (GEMINI.md / CLAUDE.md / AGENTS.md / .cursor/rules/helios.mdc / global_rules.md / copilot-instructions.md) so your personal custom rules are never overwritten:
<!-- HELIOS:START -->
# Global Agent Directives — Helios Memory Protocol (v1.5.0)
You are connected to Helios, a centralized token-budgeted memory engine.
1. Pre-Flight Check: Always call `recall_memories(scope="<current_repo>", directive_version="1.5.0")` at task start.
2. Stale Protocol: When a memory is marked `[STALE]`, inspect `anchor_files` before relying on it.
3. Write-Through DoD: Any change to ports, stacks, dependencies, or bug fixes is INCOMPLETE until `save_memory()` is called.
4. Token Diet: Keep facts atomic (<= 25 words).
5. Terminal Noise Suppression: Use quiet flags (`pytest -q --tb=short`, `docker build -q`, `git status -s`).
6. Distillation Audit: Run `/remember` before clearing context or after major milestones.
<!-- HELIOS:END -->Switch Machine Role (
workstation↔server-cli): "Runget_client_setup_bundle(action='switch_role', instance_role='server-cli')and update my directives."Clean Conversational Uninstallation: Simply tell your agent: "Uninstall Helios from this machine" (or "uninstall helios"). The agent calls
get_client_setup_bundle(action='uninstall')to safely remove the MCP entry, directive block,/rememberskill, and cognitive guard hook without clobbering your other custom rules or MCP servers.Instant Terminal 1-Liner Uninstallation:
Linux / macOS (Bash):
curl -fsSL https://<your-helios-host>/uninstall.sh | bashWindows (PowerShell):
irm https://<your-helios-host>/uninstall.ps1 | iexSelective Client: Append
?client=cursor,?client=vscode, etc. to uninstall a specific client only.
🔄 3. How Git Drift Detection Works
When you save a memory tied to configuration files, Helios watches those files across commits:
# 1. Agent saves an anchored architectural fact:
save_memory(
scope="payments-api",
category="fact",
subject="db-pool",
content="PostgreSQL connection pool runs via PgBouncer on internal port 6432.",
anchor_files=["docker-compose.yml"]
)
# 2. Later, a developer pushes a commit modifying docker-compose.yml (commit a1b2c3d).
# Helios's webhook receiver automatically flags the memory as [STALE].
# 3. Next session, the agent runs pre-flight recall_memories(scope="payments-api"):
- #14 (payments-api/fact) **[db-pool]** PostgreSQL connection pool runs via PgBouncer on internal port 6432. `[STALE: docker-compose.yml modified in commit a1b2c3d]` _(anchors: `docker-compose.yml`)_
# 4. The agent inspects docker-compose.yml:
# - If the fact is still true: calls revalidate_memories(memory_ids=[14])
# - If the port changed: calls save_memory(..., subject="db-pool", content="...") to supersede #14!sequenceDiagram
autonumber
actor Dev as Developer / Agent
participant Git as Git Provider (GitHub/Forgejo/GitLab)
participant Helios as Helios (/webhook/git)
participant SQLite as SQLite Storage
Dev->>Git: git push (modified docker-compose.yml)
Git->>Helios: POST /webhook/git (HMAC verified, <= 1MB stream)
Helios->>SQLite: Match modified files against active anchor_files
Helios->>SQLite: UPDATE memories SET status = 'stale', stale_reason = 'commit sha'
Helios->>Dev: recall_memories returns [STALE: commit sha]
Dev->>Helios: Inspect diff & call revalidate_memories([id]) or save_memory()
Helios->>SQLite: UPDATE memories SET status = 'active' (and sync Markdown exports)🏗️ 4. System Architecture
For the complete technical specification, package breakdown, and request lifecycle diagrams, see docs/ARCHITECTURE.md.
flowchart TD
subgraph Clients["AI Clients & IDEs"]
AG["Antigravity CLI / IDE"]
CR["Cursor & Windsurf"]
CD["Claude Desktop & Code"]
CX["OpenAI Codex / VS Code / OpenCode"]
end
subgraph Ingress["Ingress & Security Layer"]
AGW["AuthGateMiddleware<br/>(Bearer Token / ?token=)"]
WHG["HMAC Webhook Ingress<br/>(GitHub / Forgejo / GitLab)"]
PUB["Public Setup & Health<br/>(/setup, /setup.sh, /setup.ps1, /health)"]
end
subgraph Core["Helios Core Engine (Starlette + FastMCP)"]
MCP["MCP Streamable HTTP & SSE<br/>(/mcp, /sse)"]
AUDN["AUDN Write Gate<br/>(Word Limit & Slot Supersession)"]
REVAL["Stale Drift Evaluator<br/>& Revalidation Gate"]
CONFIG["Layered Config Engine<br/>(SQLite > Env > Default)"]
EXP["Exporter Engine<br/>(_EXPORT_LOCK)"]
end
subgraph Storage["Storage Layer (SQLite WAL Mode)"]
SQL["memory.db<br/>(busy_timeout=10000, foreign_keys=ON)"]
FTS["Virtual Table memories_fts<br/>(BM25 Full-Text Search)"]
SETTINGS["runtime_settings Table<br/>(Live Day-2 Overrides)"]
ALIASES["scope_aliases Table<br/>(Dynamic Scope Resolution)"]
end
subgraph Egress["Sync & Observability Egress"]
MD["Markdown Mirror Sync<br/>(/data/exports/<scope>.md)"]
TAR["Online SQLite Snapshot<br/>(helios_portable_bundle.tar.gz)"]
end
Clients --> AGW
Ingress --> MCP
MCP --> AUDN
MCP --> REVAL
WHG --> REVAL
AUDN --> SQL
SQL --> FTS
SQL --> SETTINGS
SQL --> ALIASES
CONFIG --> SETTINGS
SQL --> EXP
EXP --> MD
EXP --> TARLayered Configuration Precedence
Runtime settings (HELIOS_WORD_LIMIT, HELIOS_EPISODIC_TTL_DAYS, HELIOS_CHANGELOG_LIMIT, HELIOS_GIT_*) resolve dynamically on every call without container restarts, while security boundaries (HELIOS_API_KEY, HELIOS_WEBHOOK_SECRET, MEMORY_DATA_DIR) remain locked to environment variables:
flowchart LR
A["1. SQLite runtime_settings<br/>(Live via manage_server_config)"] --> B["2. Environment Variables<br/>(.env / Docker Compose)"]
B --> C["3. Built-in Safe Defaults<br/>(src/config.py)"]🛠️ 5. MCP Tools Reference
Helios exposes 11 FastMCP tools with strict Pydantic field descriptions, worker-thread offloading via anyio.to_thread.run_sync, and explicit ToolAnnotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) meeting MCP Directory and OpenAI directory static safety standards:
Tool | Key Parameters | Purpose |
|
| Search active/stale memories in |
|
| Save or supersede an atomic memory (≤ |
|
| Batch-restore |
|
| Retire/archive an obsolete memory and log the reason in the scope's changelog. |
|
| Inspect superseded and archived records for time-travel debugging. |
|
| Audit memory hygiene, detect slot collisions/near-duplicates, and prune expired episodic or abandoned stale notes. |
|
| Manage aliases ( |
|
| View or modify runtime settings live ( |
|
| Interactively list owned repos and enable/disable drift webhooks on GitHub, Forgejo, Gitea, or GitLab. |
|
| Generate client MCP configs, |
| (none) | Trigger an online SQLite backup ( |
# 1. Search active and stale memories
recall_memories(
scope: str = "global",
query: str = "",
category: Literal["rule", "fact", "preference", "episodic", ""] = "",
status_filter: Literal["all", "active", "stale"] = "all",
limit: int = 8,
include_global: bool = True,
directive_version: str = "",
) -> str
# 2. Store or supersede an atomic memory
save_memory(
scope: str,
category: Literal["rule", "fact", "preference", "episodic"],
content: str,
subject: str = "",
anchor_files: list[str] | None = None,
replaces_id: int | None = None,
) -> str
# 3. Batch-clear [STALE] flags after verifying diffs
revalidate_memories(memory_ids: list[int]) -> str
# 4. Archive an obsolete memory
deprecate_memory(memory_id: int, reason: str = "") -> str
# 5. Inspect superseded/archived audit log
recall_history(scope: str = "global", limit: int = 10) -> str
# 6. Manage aliases, view scope counts, or rename scopes
manage_scope_alias(
alias: str = "",
canonical_scope: str = "",
action: Literal["set", "remove", "list", "rename"] = "set",
) -> str
# 7. Live Day-2 server configuration
manage_server_config(
action: Literal["list", "set", "reset"] = "list",
key: str = "",
value: str = "",
) -> str
# 8. Conversational Git webhook management
manage_git_webhooks(
action: Literal["list", "enable", "disable"] = "list",
repos: list[str] | None = None,
include_forks: bool = False,
) -> str
# 9. Client onboarding & lifecycle management
get_client_setup_bundle(
client: Literal[
"antigravity",
"cursor",
"claude-desktop",
"claude-code",
"codex",
"windsurf",
"vscode",
"opencode",
"all",
] = "all",
os_platform: Literal["linux", "macos", "windows", "auto"] = "auto",
instance_role: Literal["workstation", "server-cli"] = "workstation",
action: Literal["install_or_update", "switch_role", "uninstall"] = "install_or_update",
) -> str
# 10. Generate crash-safe portable backup archive
export_bundle() -> str
# 11. Audit memory health and prune obsolete facts
distill_memories(
scope: str = "global",
action: Literal["audit", "prune", "suggest"] = "audit",
dry_run: bool = True,
stale_age_days: int = 30,
) -> str🌐 6. HTTP Endpoints & Organization Webhooks
6.1 HTTP Routes Reference
Method & Path | Auth Required | Description |
| No (Redacted) / Yes (Full) | Returns service health. Redacts database telemetry when |
| No | AI onboarding guide with non-destructive MCP config snippets. Accepts optional |
| No | 1-liner Linux/macOS Bash client installer ( |
| No | 1-liner Windows PowerShell client installer ( |
| No | AI uninstallation guide ( |
| No | 1-liner Linux/macOS Bash uninstaller ( |
| No | 1-liner Windows PowerShell uninstaller ( |
| Yes (if key set) | Lists generated Markdown scope export files and sizes. |
| Yes (if key set) | Generates and downloads |
| HMAC Signature | Universal Git push webhook receiver for |
| Yes (if key set) | MCP Streamable HTTP endpoint for modern protocol clients. |
| Yes (if key set) | MCP Server-Sent Events endpoint with session message support. |
6.2 Optional: Account-Wide / Organization Webhooks
In addition to selective per-repo activation via manage_git_webhooks, you can configure a single global webhook on your Git server:
Forgejo / Gitea: Go to Site Administration → Default Webhooks (
/admin/hooks) or Organization Settings → Webhooks, addhttps://<helios-host>/webhook/git(POST,application/json,HELIOS_WEBHOOK_SECRET, Push Events).GitHub: Go to Organization Settings → Webhooks, add
https://<helios-host>/webhook/git(application/json,HELIOS_WEBHOOK_SECRET, Just the push event).
🧪 7. Testing & Local Development
The test suite is modularized to mirror application packages (tests/middleware/, tests/routes/, tests/tools/) with centralized environment isolation in tests/conftest.py:
# Set up virtual environment
python3 -m venv .venv
source .venv/bin/activate
# Install development dependencies
pip install -r requirements-dev.txt
# Run linter & complete test suite
ruff check src/ tests/
pytest tests/ -v
# Or run targeted sub-suites
pytest tests/middleware/ -v
pytest tests/routes/ -v
pytest tests/tools/ -v
# Validate declarative seed fact invariants
python -m src.seed --check📄 License
Helios is open-source software licensed under the GNU Affero General Public License v3.0 (AGPL-3.0-only).
See CONTRIBUTING.md for contribution guidelines and SECURITY.md for vulnerability reporting.
Available Tools
11 toolsdeprecate_memoryADestructiveIdempotent
Archive an obsolete active or stale memory by ID without deleting its historical audit record. Transitions status to 'archived', sets the valid_to timestamp, logs the deprecation reason in the scope changelog, and updates Markdown exports. Archived records are excluded from recall_memories but remain permanently inspectable via recall_history. Use deprecate_memory when a fact or rule no longer applies and has no replacement; use save_memory instead to overwrite an outdated fact with a new value, or revalidate_memories if a [STALE] memory is still accurate.
Inputs: memory_id (required), reason. Returns: result
distill_memoriesADestructiveIdempotent
Audit scope memory health, suggest duplicate slot consolidations, or prune expired episodic and abandoned stale records. action='audit' (default) and action='suggest' are read-only diagnostics; action='prune' archives expired episodic notes and stale memories older than stale_age_days, but is gated by dry_run=True by default (set dry_run=False to commit changes and sync Markdown exports). Use distill_memories for periodic scope-wide hygiene; use deprecate_memory to retire a single obsolete memory ID, or save_memory with replaces_id to apply consolidation suggestions.
Inputs: scope, action, dry_run, stale_age_days. Returns: result
export_bundleAIdempotent
Create or overwrite a portable backup archive (helios_portable_bundle.tar.gz) on the server filesystem. Uses the SQLite Online Backup API to capture a crash-safe snapshot of memory.db alongside all Markdown exports without locking concurrent readers or writers, leaving database records untouched. Use export_bundle for server backups and migration snapshots; use get_client_setup_bundle instead to generate IDE/CLI configuration snippets, or recall_memories to query stored facts.
Inputs: no named parameters. Returns: result
get_client_setup_bundleARead-onlyIdempotent
Generate read-only client onboarding configs, idempotent global agent directives (), and /remember skill files for local AI tools. Supports full client lifecycle management via action: 'install_or_update' outputs non-destructive MCP and directive snippets tailored to client, os_platform, and instance_role ('workstation' vs headless 'server-cli'); 'switch_role' updates role-specific rules; 'uninstall' provides surgical removal instructions that preserve user custom rules. Use get_client_setup_bundle to install, reconfigure, or uninstall Helios on a client machine; use manage_server_config to modify server-side settings, or export_bundle to back up the database.
Inputs: action, client, os_platform, instance_role. Returns: result
manage_git_webhooksADestructive
List, enable, or disable remote Git push webhooks for anchor_files drift detection across Forgejo, Gitea, GitHub, or GitLab. Requires HELIOS_GIT_TOKEN and HELIOS_WEBHOOK_URL (returns manual setup instructions if unconfigured): action='list' audits owned repos, action='enable' installs an HMAC-signed push webhook on each target in repos, and action='disable' deletes only the Helios webhook from the remote repositories without affecting code or stored memories. Always run action='list' and confirm target repos with the user before calling 'enable' or 'disable'. Use manage_git_webhooks to manage remote repository hooks; use manage_server_config to set HELIOS_GIT_* settings, or revalidate_memories to clear [STALE] flags after a push.
Inputs: repos, action, include_forks. Returns: result
manage_scope_aliasADestructive
Manage project alias mappings and migrate memory scopes in SQLite. action='list' is read-only and returns all aliases plus per-scope active/stale counts; action='set' maps alias to canonical_scope; action='remove' deletes only the alias mapping while leaving stored memories untouched; action='rename' destructively migrates all memories from alias into canonical_scope, registers the alias, and syncs Markdown exports. 'set' and 'rename' require both alias and canonical_scope, while 'remove' requires alias. Use manage_scope_alias to unify repository names or rename projects; use manage_server_config for server tunables or distill_memories to clean up memories within a scope.
Inputs: alias, action, canonical_scope. Returns: result
manage_server_configAIdempotent
Inspect, override, or reset live Helios runtime settings in SQLite without restarting the server. action='list' returns all settings with secrets redacted; action='set' (requires key and value) persists an immediate runtime override; action='reset' (requires key) removes the SQLite override to revert to environment or default values. Security-locked keys (HELIOS_API_KEY, HELIOS_WEBHOOK_SECRET, MEMORY_DATA_DIR) cannot be altered at runtime, and changing HELIOS_GIT_API_URL or HELIOS_GIT_PROVIDER automatically clears any stored runtime HELIOS_GIT_TOKEN. Use manage_server_config for server-side tunables; use get_client_setup_bundle for local IDE/CLI onboarding or manage_scope_alias for project scope mappings.
Inputs: key, value, action. Returns: result
recall_historyARead-onlyIdempotent
Retrieve superseded and archived memory records for a scope to audit configuration history and slot lineage. Read-only: resolves scope aliases and returns up to limit (1-25) historical entries ordered by valid_to descending, including validity timestamps and superseding memory IDs. Use recall_history for time-travel debugging or reviewing retired facts; use recall_memories instead to search current active or [STALE] memories.
Inputs: limit, scope. Returns: result
recall_memoriesARead-onlyIdempotent
Search active and stale memories in Helios using SQLite FTS5 BM25 ranking and category priority (rule > fact > preference > episodic). Read-only: resolves scope aliases, merges 'global' rules when include_global=True, returns top priority records when query is empty, and emits a warning if directive_version lags the server. If any returned memory is flagged [STALE], inspect its anchor_files before acting and resolve via revalidate_memories or save_memory. Use recall_memories at task start for current state; use recall_history instead to inspect superseded or archived records.
Inputs: limit, query, scope, category, +3 more. Returns: result
revalidate_memoriesAIdempotent
Restore a batch of [STALE] memories back to 'active' status after verifying that changes to their anchor_files did not invalidate them. Clears stale_reason and stale_since for all valid stale IDs in memory_ids and syncs Markdown exports; non-existent or already-active IDs are safely skipped and reported without failing the batch. Use revalidate_memories only when the recorded fact remains accurate after a commit; use save_memory instead to supersede the fact if its value changed, or deprecate_memory if it was removed.
Inputs: memory_ids (required). Returns: result
save_memoryAIdempotent
Create or supersede an atomic memory (<= 25 words) in SQLite and synchronize Markdown scope exports. Saving to an existing (scope, subject) slot or passing replaces_id automatically marks the prior active memory as 'superseded', while identical content is a safe idempotent no-op. Providing repo-relative anchor_files links the memory to Git push webhooks so commits touching those files automatically flag it [STALE]. Use save_memory to add or update facts and rules; use deprecate_memory to archive obsolete facts without replacement, revalidate_memories to clear [STALE] flags when facts remain valid, or distill_memories for bulk cleanup.
Inputs: scope (required), content (required), category (required), subject, +2 more. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose, and the descriptions go further by explicitly naming sibling tools to use instead (e.g. save_memory vs deprecate_memory vs revalidate_memories). Subtle boundaries like recall_memories vs recall_history vs distill_memories audit are spelled out as current-state vs history vs hygiene, so an agent can select reliably.
All 11 tools follow a consistent snake_case verb_noun pattern (export_bundle, recall_memories, save_memory, manage_server_config, distill_memories). The verb set (export, recall, save, deprecate, revalidate, manage, get, distill) is varied but predictable and readable.
Eleven tools sit squarely in the well-scoped 3-15 range, and each maps to a distinct capability (backup, onboarding, config, webhooks, scope aliases, and the memory CRUD/history/hygiene lifecycle). No tool feels redundant or like filler.
The memory lifecycle is well covered: create/supersede, recall, history, deprecate, revalidate, prune, plus scope, config, webhook, and backup management. Minor gaps exist—export_bundle has no corresponding import/restore tool, and there is no way to un-archive a memory—but agents can work around these.
Maintenance
Related MCP Connectors
Persistent memory for AI agents, for code, research and everyday life. Stale facts retire.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Shared memory for your AI agents. Every fact shows its source, and stale facts get replaced.
Persistent engineering memory designed to follow developers across coding agents.
Related MCP Servers
- AlicenseAqualityDmaintenancePersistent shared memory for AI coding agents. Stores facts as entity/key/value triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.16235 npm5AGPL 3.0
- AlicenseBqualityBmaintenancePersistent memory for AI coding agents, storing learned architecture decisions, patterns, and bug fixes in a local SQLite database with full-text search, enabling agents to recall information across sessions.6464 npm1MIT
- AlicenseNot gradedqualityDmaintenancePersistent memory for AI coding agents with local-first, zero-cost, privacy-first SQLite/FTS5 storage and biological-inspired decay.19 npm3MIT

robo-cortexofficial
AlicenseAqualityBmaintenanceProvides a git-aware knowledge base for AI coding agents to store and retrieve memories anchored to code changes, with automatic staleness detection.9211 PyPI1MIT