token-budget-langchain — Memory Workflow
Integrate structural LangChain message conversion and TokenBudgetMemory with explicit keys, durable eviction semantics and compatibility checks.
$1
Works with the AI Agents you already use
token-budget-langchain — Memory Workflow
Example session with this skill installed
Use token-budget-langchain-workflow to integrate this package and run its local fixture, keeping unverified provider behavior explicit.
- Read your context and instructions
- Compiled the token-budget-langchain
Local synthetic fixture result from the published package: {"historyMessages":2,"roles":["human","ai"]}
Interpretation: Plain structural objects, not SDK class instances. Baseline @langchain/core ^0.3.0 shapes. Missing explicit keys/non-string values can omit turns. Generic custom roles map to user; legacy FunctionMessage linkage needs a matching preceding call. No durable graph-store guarantee.
Next validation: Save/load a deterministic human/AI turn with explicit keys and assert roles. Pressure-test history and compare raw budget before/after saveContext commit. Test multi-key/non-string inputs and metadata/tool calls used by the real app. Verify tenant/session isolation; never clear shared production memory for a test.
Evidence scope: source version 0.1.5 suite passed 28 tests; published 0.1.4 was separately exercised with the included fixture. These are distinct baselines. Live provider/SDK/backend behavior was not tested, and no network service credential was needed for the example.
Connects securely to your tools. The creator never sees your data.
About this skill
Integrate structural LangChain message conversion and TokenBudgetMemory with explicit keys, durable eviction semantics and compatibility checks.
Original application-integration playbook covering setup, exact supported exports, migration, failure handling and local verification. This is a curated workflow package, not a new MCP server or automatic host-context control.
Verified source 0.1.5: 28 tests passed. The included local fixture also passed against published npm 0.1.4 tarball code using peer/dependency resolution from the reviewed monorepo, not an independent clean-consumer install. No live provider, embedding service or telemetry backend was contacted.
Limitations: Plain structural objects, not SDK class instances. Baseline @langchain/core ^0.3.0 shapes. Missing explicit keys/non-string values can omit turns. Generic custom roles map to user; legacy FunctionMessage linkage needs a matching preceding call. No durable graph-store guarantee.
The separate npm runtime remains free/open-source under MIT at https://github.com/shivam039/token-budget/tree/main/packages/token-budget-langchain. MIT notice is preserved; this $1 purchase is for original curated workflow instructions, not exclusive runtime access. Provider/exporter services, if selected, are separately authorized and may charge. No runtime dependencies are bundled and no blanket dependency-security clearance is promised.
Plain structural objects, not SDK class instances. Baseline @langchain/core ^0.3.0 shapes. Missing explicit keys/non-string values can omit turns. Generic custom roles map to user; legacy FunctionMessage linkage needs a matching preceding call. No durable graph-store guarantee.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 19 days ago
Requires
Permissions
Allowed Hosts
Project-scoped setup, edits and synthetic local fixtures. No provider/exporter endpoint is configured by this skill. Any live data transmission or optional service use requires the authorized destination and scope; never include credentials in evidence.