AgentHelm wraps any agent framework with human-in-the-loop approvals, audit trails, budget guardrails, and a shared Project Brain — so autonomous agents stay accountable, on-budget, and recoverable.
Free for 1 agent & 1 project · No credit card required
Every time your agent starts a new session, it begins with a blank slate. No memory of past decisions, configuration patterns, or API specifications.
Agents don't remember project architecture, API choices, or database migrations. Every run starts from scratch.
Engineering context is locked in single agent sessions. What one agent learns is lost to all others on the codebase.
Without shared project standards, agents write code using deprecated functions or insecure library wrappers.
AgentHelm builds a shared memory repository that persists across agents, sessions, and platforms.
A centralized, version-controlled knowledge base containing repo styling schemas, API declarations, and design rules.
Rank and select knowledge segments dynamically to supply relevant context rules to agents before they start writing.
Agents propose newly discovered project decisions back into the ingestion validation queue, keeping the brain up-to-date.
Knowledge flows through a secure pipeline: proposal → noise filter → validation → verification → analysis → merge planning → publishing → Project Brain → context injection.
Sarvam-105B classifies raw agent observations as worth compiling or routine noise, before they're considered as a formal proposal
Agent submits knowledge proposal containing decisions, files, APIs, DB changes
Strips secrets, PII, normalizes markdown formatting, validates schema structure
Check tool scopes allowlist (@read, @side_effect, @irreversible)
Validate agent registration state and active JWT token signatures
Heuristics-based trust scoring and project configuration validation
Inspect active brain entries for logical overrides and structural conflicts
Execute logical additions, mark supersessions, and commit changes
Commit update to active database state and publish version tag
Update shared brain ready for semantic context injection to active agents
Expose the Project Brain directly to your IDE agents. AgentHelm is natively compatible with Claude Code, Cursor, Windsurf, and Claude Desktop using the Model Context Protocol.
Configure Claude Desktop to read/write to the Project Brain automatically.
{
"mcpServers": {
"agenthelm": {
"command": "npx",
"args": ["-y", "agenthelm-mcp"],
"env": {
"AGENTHELM_CONNECT_KEY": "ahe_live_...",
"AGENTHELM_PROJECT": "my-production-app",
"AGENTHELM_BASE_URL": "https://agenthelm.online"
}
}
}
}Every layer hardened. Fail-closed by default. Scoped credentials, tenant isolation, and a complete audit trail.
Every SDK request runs authenticated via JSON Web Tokens. Agent tokens are generated during handshakes, expire in 12 hours, and are validated using secure HSM key hashes.
Enforce safety bounds on agent execution. Declare agent actions using decorators like @read, @side_effect, or @irreversible. Force human approval on irreversible actions.
Maintain complete accountability for agent choices. Every context injection, knowledge proposal, and reasoning decision is tracked with permanent timestamp logs.
Actively monitor for runaway agents. Detect token consumption spikes, silent crashes, and high error rate thresholds instantly to protect backend billing APIs.
Agent Silent Connection
Monitored at ingest. Auto-transitions to 'stopped' state if liveness heartbeat fails.
Validation Error
Rejected immediately. Never merges into target Project Brain. Emits warning code.
Permissions Defect
Blocked at runtime. Throws immediate SDK exception. Logs event to security alerts.
Correlate logs, track percentiles, and check agent health metrics directly inside your control panel.
Calculate processing percentiles directly inside the backend engine. Buffer stage events and group metrics dynamically by step.
Zero-dependency structured logs. Capture agent activity, duration timings, status codes, and error trace identifiers.
Trace requests from agent script to DB. Associate every reasoning decision and context injection with unique transaction IDs.
Proactive service checks. Monitor database readiness, ping response speeds, and active memory queue bounds.
Choose your runtime language. Same core capabilities, security boundaries, and telemetry correlation.
pip install agenthelm-sdkimport agenthelmdock = agenthelm.connect("ahe_live_...", name="My Agent")npm install agenthelm-node-sdkconst { AgentHelm } = require('agenthelm-node-sdk')const dock = new AgentHelm("ahe_live_...", { name: "My Agent" })curl -H 'Authorization: Bearer ***'Language agnostic HTTP client requestsPOST /api/sdk/proposals
POST /api/sdk/inject
POST /api/sdk/pingToken-budgeted relevance scoring. Injects only the most relevant brain entries for the current task hint.
Automatically persist agent state snapshots. Resume from precise step index on failures.
@read, @side_effect, @irreversible declarations. Hold dangerous operations for approval.
Receive immediate notifications on high errors, token consumption spikes, or liveness failures.
Trace events correlated with UUID transaction identifiers. Clean JSON logs emitted to console.
Compute duration averages and p95 latency statistics per pipeline stage in memory.
AgentHelm sits between your agents and the brain. Any framework. Any model. Any cloud.
Claude Code
IDE-native agent with full repo context
Cursor
AI-first editor with Composer
Codex
OpenAI's coding agent
GitHub Copilot
Chat & inline completions
Windsurf
Cascade agentic flows
Cline
Autonomous coding assistant
CrewAI
Role-based multi-agent crews
LangGraph
Stateful graph orchestration
AutoGen
Microsoft's multi-agent framework
OpenAI Assistants
Built-in tool use & threads
Semantic Kernel
Microsoft's AI orchestration
Haystack
RAG & agent pipelines
OpenAI
GPT-4o, o1, embeddings
Anthropic
Claude 3.5 Sonnet, Haiku
Gemini 1.5 Pro, Flash
Mistral
Large, Medium, Small models
Groq
Ultra-fast inference
Ollama
Local model hosting
Supabase
Postgres + Auth + Realtime
Vercel
Edge functions & hosting
Docker
Containerized agent deployments
Kubernetes
Orchestrated agent clusters
Redis
Caching & pub/sub for agents
Telegram
Mobile agent control
AgentHelm's SDK wraps any agent framework. No vendor lock-in. Switch frameworks without rewriting your governance layer.
Start free, scale with Pro, or power your entire engineering fleet on Team.
₹0
For solo developers exploring shared project brain intelligence.
₹499/mo
For professional builders running multi-agent workflows.
₹1,999/mo
For engineering organizations managing shared agent fleets.
| Feature | Free | Pro | Team |
|---|---|---|---|
| Monthly Credits | 100 | 2,000 | 10,000 |
| Max Agents | 1 | 3 | 10 |
| Max Brain Entries | 50 | 500 | Unlimited |
| Sarvam Document Intelligence | |||
| Cross-Agent Analytics | |||
| Policy Engine Modes | Gated Only | All Modes | All Modes + Auto |
Explore standard guides, integration specs, and copy-paste examples to wire up your agents.
# pip install agenthelm-sdk
import agenthelm
dock = agenthelm.connect(
"ahe_live_...",
name="research-agent"
)
# Submit knowledge proposal
dock.propose(
summary="Added user auth module",
decisions=["JWT with refresh tokens"],
files_modified=["auth/jwt.py", "auth/models.py"],
apis_affected=["POST /auth/login"],
)
# Inject context for a task
context = dock.inject(
project="my-project",
task_hint="Implement password reset"
)
// npm install agenthelm-node-sdk
const { AgentHelm } = require('agenthelm-node-sdk')
const dock = new AgentHelm("ahe_live_...", {
name: "payment-agent"
})
// Submit knowledge proposal
await dock.propose({
summary: "Stripe webhook handler",
decisions: ["Idempotency keys required"],
files_modified: ["payments/webhook.js"],
apis_affected: ["POST /webhooks/stripe"],
})
// Inject context
const context = await dock.inject({
project: "my-project",
task_hint: "Handle subscription cancellation"
})
# Submit proposal
curl -X POST https://api.agenthelm.online/api/sdk/proposals \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"project": "my-project",
"content_hash": "abc123...",
"payload": {
"summary": "Database migration v3",
"decisions": ["Add idx on user_email"],
"db_changes": ["ALTER TABLE users ADD INDEX..."]
}
}'
# Inject context
curl -X POST https://api.agenthelm.online/api/sdk/inject \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"project": "my-project",
"task_hint": "Optimize slow query"
}'
Start free forever for up to 3 agents · Integrate in 5 minutes
Everything you need to know about governing autonomous agents in production.
Still curious? Read the docs or start free.